Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3497 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6670. Min Range: -7.6670
Max Act: 7.6670. Min Act: -0.1700
Data Index: 6608624 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6670. Min Range: -7.6670
Max Act: 7.6045. Min Act: -0.1700
Data Index: 3682952 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6670. Min Range: -7.6670
Max Act: 7.1358. Min Act: -0.1700
Data Index: 5340971 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6670. Min Range: -7.6670
Max Act: 7.0733. Min Act: -0.1700
Data Index: 3677798 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6670. Min Range: -7.6670
Max Act: 7.0420. Min Act: -0.1700
Data Index: 4393985 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.8233. Min Act: -0.1700
Data Index: 2731728 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.7608. Min Act: -0.1700
Data Index: 1630905 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.6983. Min Act: -0.1700
Data Index: 2446108 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.5733. Min Act: -0.1700
Data Index: 4646522 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.5733. Min Act: -0.1700
Data Index: 3313226 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.5420. Min Act: -0.1700
Data Index: 218618 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.5420. Min Act: -0.1700
Data Index: 2945843 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.4483. Min Act: -0.1700
Data Index: 7647214 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.4483. Min Act: -0.1700
Data Index: 4378822 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.4483. Min Act: -0.1700
Data Index: 2687054 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.4170. Min Act: -0.1700
Data Index: 6450816 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.4170. Min Act: -0.1700
Data Index: 4272088 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.4170. Min Act: -0.1700
Data Index: 2100624 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.3858. Min Act: -0.1700
Data Index: 6551258 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6670. Min Range: -7.6670
Max Act: 6.3858. Min Act: -0.1700
Data Index: 1900622 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19