Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4587 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.4717. Min Act: -0.1700
Data Index: 843582 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.4717. Min Act: -0.1700
Data Index: 6882222 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.4092. Min Act: -0.1700
Data Index: 3770731 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.4405. Min Act: -0.1700
Data Index: 1397363 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.4092. Min Act: -0.1700
Data Index: 5550137 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.4092. Min Act: -0.1700
Data Index: 510048 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.2842. Min Act: -0.1700
Data Index: 116188 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.2530. Min Act: -0.1700
Data Index: 369511 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.1592. Min Act: -0.1700
Data Index: 2121802 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.0967. Min Act: -0.1700
Data Index: 7218473 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.1280. Min Act: -0.1700
Data Index: 5999687 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.0655. Min Act: -0.1700
Data Index: 7811485 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.0967. Min Act: -0.1700
Data Index: 1951794 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.0655. Min Act: -0.1700
Data Index: 7416524 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.0342. Min Act: -0.1700
Data Index: 1397362 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.0030. Min Act: -0.1700
Data Index: 8420493 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4717. Min Range: -7.4717
Max Act: 7.0342. Min Act: -0.1700
Data Index: 4430357 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4717. Min Range: -7.4717
Max Act: 6.9717. Min Act: -0.1700
Data Index: 2076054 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4717. Min Range: -7.4717
Max Act: 6.9717. Min Act: -0.1700
Data Index: 7850338 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4717. Min Range: -7.4717
Max Act: 6.9717. Min Act: -0.1700
Data Index: 305526 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19