Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4981 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.7983. Min Act: -0.1700
Data Index: 7732955 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.7046. Min Act: -0.1700
Data Index: 3081010 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.6108. Min Act: -0.1700
Data Index: 607606 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.5796. Min Act: -0.1700
Data Index: 5852477 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.5171. Min Act: -0.1700
Data Index: 653483 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.4858. Min Act: -0.1700
Data Index: 4199728 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.4858. Min Act: -0.1700
Data Index: 778769 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.4858. Min Act: -0.1700
Data Index: 1945027 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.4546. Min Act: -0.1700
Data Index: 269882 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.4233. Min Act: -0.1700
Data Index: 799898 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.4233. Min Act: -0.1700
Data Index: 5623975 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.4233. Min Act: -0.1700
Data Index: 4955259 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.4546. Min Act: -0.1700
Data Index: 8286279 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.4233. Min Act: -0.1700
Data Index: 204681 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.4233. Min Act: -0.1700
Data Index: 7118707 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.4233. Min Act: -0.1700
Data Index: 157051 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.3921. Min Act: -0.1700
Data Index: 7199904 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.3921. Min Act: -0.1700
Data Index: 8150063 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.3296. Min Act: -0.1700
Data Index: 7304004 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7983. Min Range: -4.7983
Max Act: 4.3608. Min Act: -0.1700
Data Index: 6972529 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19