Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2537 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.3960. Min Act: -0.1700
Data Index: 1931120 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2705. Min Act: -0.1700
Data Index: 186720 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2548. Min Act: -0.1700
Data Index: 6950688 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2391. Min Act: -0.1700
Data Index: 3588360 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2076. Min Act: -0.1700
Data Index: 816340 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2076. Min Act: -0.1700
Data Index: 2430220 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2076. Min Act: -0.1700
Data Index: 7953550 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.1919. Min Act: -0.1700
Data Index: 5615129 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.1604. Min Act: -0.1700
Data Index: 1969039 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.1447. Min Act: -0.1700
Data Index: 3841773 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.1289. Min Act: -0.1700
Data Index: 4488994 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.1289. Min Act: -0.1700
Data Index: 8448181 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.1289. Min Act: -0.1700
Data Index: 3611971 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.0974. Min Act: -0.1700
Data Index: 6309621 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.0974. Min Act: -0.1700
Data Index: 4799152 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.0974. Min Act: -0.1700
Data Index: 5175942 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.0817. Min Act: -0.1700
Data Index: 4212014 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.0817. Min Act: -0.1700
Data Index: 8615046 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.0817. Min Act: -0.1700
Data Index: 8170861 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.0659. Min Act: -0.1700
Data Index: 4285260 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19