Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 189 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1692. Min Range: -6.1692
Max Act: 6.1692. Min Act: -0.1700
Data Index: 3284560 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1692. Min Range: -6.1692
Max Act: 6.1380. Min Act: -0.1700
Data Index: 3136008 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1692. Min Range: -6.1692
Max Act: 6.0755. Min Act: -0.1700
Data Index: 7664332 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1692. Min Range: -6.1692
Max Act: 6.0755. Min Act: -0.1700
Data Index: 8748173 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1692. Min Range: -6.1692
Max Act: 6.0755. Min Act: -0.1700
Data Index: 6441426 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1692. Min Range: -6.1692
Max Act: 6.0130. Min Act: -0.1700
Data Index: 6707674 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1692. Min Range: -6.1692
Max Act: 5.9817. Min Act: -0.1700
Data Index: 6138579 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1692. Min Range: -6.1692
Max Act: 6.0130. Min Act: -0.1700
Data Index: 1356800 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1692. Min Range: -6.1692
Max Act: 5.9817. Min Act: -0.1700
Data Index: 4359411 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1692. Min Range: -6.1692
Max Act: 5.9505. Min Act: -0.1700
Data Index: 649157 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1692. Min Range: -6.1692
Max Act: 5.9505. Min Act: -0.1700
Data Index: 8245725 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1692. Min Range: -6.1692
Max Act: 5.9505. Min Act: -0.1700
Data Index: 8729287 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1692. Min Range: -6.1692
Max Act: 5.9505. Min Act: -0.1700
Data Index: 8753422 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1692. Min Range: -6.1692
Max Act: 5.9192. Min Act: -0.1700
Data Index: 4551492 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1692. Min Range: -6.1692
Max Act: 5.8880. Min Act: -0.1700
Data Index: 5878403 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1692. Min Range: -6.1692
Max Act: 5.8880. Min Act: -0.1700
Data Index: 906163 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1692. Min Range: -6.1692
Max Act: 5.8567. Min Act: -0.1700
Data Index: 8125021 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1692. Min Range: -6.1692
Max Act: 5.8880. Min Act: -0.1700
Data Index: 1311974 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1692. Min Range: -6.1692
Max Act: 5.8567. Min Act: -0.1700
Data Index: 6828532 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1692. Min Range: -6.1692
Max Act: 5.8567. Min Act: -0.1700
Data Index: 2597645 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19