Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5168 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4754. Min Range: -5.4754
Max Act: 5.4754. Min Act: -0.1700
Data Index: 4805734 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4754. Min Range: -5.4754
Max Act: 5.2567. Min Act: -0.1700
Data Index: 463350 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4754. Min Range: -5.4754
Max Act: 5.1942. Min Act: -0.1700
Data Index: 8786882 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4754. Min Range: -5.4754
Max Act: 5.1317. Min Act: -0.1700
Data Index: 782291 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4754. Min Range: -5.4754
Max Act: 5.1004. Min Act: -0.1700
Data Index: 916317 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4754. Min Range: -5.4754
Max Act: 5.0379. Min Act: -0.1700
Data Index: 3339667 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4754. Min Range: -5.4754
Max Act: 4.9754. Min Act: -0.1700
Data Index: 4345286 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4754. Min Range: -5.4754
Max Act: 4.9442. Min Act: -0.1700
Data Index: 4339023 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4754. Min Range: -5.4754
Max Act: 4.9129. Min Act: -0.1700
Data Index: 3561939 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4754. Min Range: -5.4754
Max Act: 4.8817. Min Act: -0.1700
Data Index: 4437038 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4754. Min Range: -5.4754
Max Act: 4.8192. Min Act: -0.1700
Data Index: 815693 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4754. Min Range: -5.4754
Max Act: 4.8192. Min Act: -0.1700
Data Index: 3123937 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4754. Min Range: -5.4754
Max Act: 4.8192. Min Act: -0.1700
Data Index: 6973984 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4754. Min Range: -5.4754
Max Act: 4.8192. Min Act: -0.1700
Data Index: 7878348 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4754. Min Range: -5.4754
Max Act: 4.8192. Min Act: -0.1700
Data Index: 669192 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4754. Min Range: -5.4754
Max Act: 4.7879. Min Act: -0.1700
Data Index: 8453808 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4754. Min Range: -5.4754
Max Act: 4.7567. Min Act: -0.1700
Data Index: 2823519 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4754. Min Range: -5.4754
Max Act: 4.7879. Min Act: -0.1700
Data Index: 4247353 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4754. Min Range: -5.4754
Max Act: 4.7879. Min Act: -0.1700
Data Index: 7498311 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4754. Min Range: -5.4754
Max Act: 4.7879. Min Act: -0.1700
Data Index: 6584197 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19