Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 735 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.4526. Min Act: -0.1700
Data Index: 7431267 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.4526. Min Act: -0.1700
Data Index: 6168891 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.3901. Min Act: -0.1700
Data Index: 4033867 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.3901. Min Act: -0.1700
Data Index: 4556414 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.3588. Min Act: -0.1700
Data Index: 621278 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.3588. Min Act: -0.1700
Data Index: 3343051 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2963. Min Act: -0.1700
Data Index: 7808963 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2651. Min Act: -0.1700
Data Index: 5073257 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2651. Min Act: -0.1700
Data Index: 1479909 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2651. Min Act: -0.1700
Data Index: 8237256 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2651. Min Act: -0.1700
Data Index: 1073938 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2651. Min Act: -0.1700
Data Index: 1642952 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2338. Min Act: -0.1700
Data Index: 4159927 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2338. Min Act: -0.1700
Data Index: 6504076 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2338. Min Act: -0.1700
Data Index: 5973612 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2338. Min Act: -0.1700
Data Index: 3159711 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2026. Min Act: -0.1700
Data Index: 5464468 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2026. Min Act: -0.1700
Data Index: 3100704 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2026. Min Act: -0.1700
Data Index: 2367626 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2026. Min Act: -0.1700
Data Index: 4799852 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19