Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2934 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.9416. Min Act: -0.1700
Data Index: 3786605 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.9416. Min Act: -0.1700
Data Index: 7118138 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.9416. Min Act: -0.1700
Data Index: 2906522 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.8791. Min Act: -0.1700
Data Index: 7393342 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.8791. Min Act: -0.1700
Data Index: 8704597 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.6916. Min Act: -0.1700
Data Index: 6687782 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.4416. Min Act: -0.1700
Data Index: 6292257 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.3791. Min Act: -0.1700
Data Index: 4786594 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.3791. Min Act: -0.1700
Data Index: 7039033 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.3791. Min Act: -0.1700
Data Index: 5674609 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.3166. Min Act: -0.1700
Data Index: 2756032 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.1916. Min Act: -0.1699
Data Index: 5802332 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.2541. Min Act: -0.1700
Data Index: 7435303 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.2541. Min Act: -0.1700
Data Index: 5451313 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.2541. Min Act: -0.1700
Data Index: 4438560 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.2541. Min Act: -0.1700
Data Index: 1761914 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.1916. Min Act: -0.1700
Data Index: 7394542 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.1916. Min Act: -0.1700
Data Index: 7432480 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.1916. Min Act: -0.1700
Data Index: 4543183 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9416. Min Range: -11.9416
Max Act: 11.1916. Min Act: -0.1700
Data Index: 4379613 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19