Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1448 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.2858. Min Act: -0.1700
Data Index: 8490726 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.2546. Min Act: -0.1700
Data Index: 2975388 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.1296. Min Act: -0.1700
Data Index: 8396542 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.0983. Min Act: -0.1700
Data Index: 8233226 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.0983. Min Act: -0.1700
Data Index: 2961040 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.0671. Min Act: -0.1700
Data Index: 6423059 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.0671. Min Act: -0.1700
Data Index: 1900987 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.0671. Min Act: -0.1700
Data Index: 2961039 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.0358. Min Act: -0.1700
Data Index: 5745727 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.0046. Min Act: -0.1700
Data Index: 3954843 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.0046. Min Act: -0.1700
Data Index: 1147951 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.0046. Min Act: -0.1700
Data Index: 8233232 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.0046. Min Act: -0.1700
Data Index: 5478324 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.0046. Min Act: -0.1700
Data Index: 1004090 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.0046. Min Act: -0.1700
Data Index: 510570 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2858. Min Range: -6.2858
Max Act: 6.0046. Min Act: -0.1700
Data Index: 6585386 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2858. Min Range: -6.2858
Max Act: 5.9733. Min Act: -0.1700
Data Index: 8673998 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2858. Min Range: -6.2858
Max Act: 5.9421. Min Act: -0.1700
Data Index: 4999780 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2858. Min Range: -6.2858
Max Act: 5.9421. Min Act: -0.1700
Data Index: 1998393 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2858. Min Range: -6.2858
Max Act: 5.9421. Min Act: -0.1694
Data Index: 1660329 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19