Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.7115. Min Act: -0.1700
Data Index: 998514 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.6490. Min Act: -0.1700
Data Index: 3468315 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.6177. Min Act: -0.1700
Data Index: 3900045 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.5865. Min Act: -0.1700
Data Index: 7796292 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.6177. Min Act: -0.1700
Data Index: 3239161 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.5240. Min Act: -0.1700
Data Index: 881244 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.5552. Min Act: -0.1700
Data Index: 4582738 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.4927. Min Act: -0.1700
Data Index: 620561 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.4927. Min Act: -0.1700
Data Index: 1389741 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.4927. Min Act: -0.1700
Data Index: 5760108 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.4302. Min Act: -0.1700
Data Index: 1139764 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.3990. Min Act: -0.1700
Data Index: 8185639 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.4302. Min Act: -0.1700
Data Index: 911645 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.4302. Min Act: -0.1700
Data Index: 1143353 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.4302. Min Act: -0.1700
Data Index: 5018779 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.3677. Min Act: -0.1700
Data Index: 620556 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.3677. Min Act: -0.1700
Data Index: 8057904 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.3677. Min Act: -0.1700
Data Index: 8058907 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.3677. Min Act: -0.1700
Data Index: 549023 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.3677. Min Act: -0.1700
Data Index: 7505001 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19