Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4362 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1671. Min Range: -7.1671
Max Act: 7.1671. Min Act: -0.1700
Data Index: 5900650 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.9796. Min Act: -0.1700
Data Index: 906423 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.8546. Min Act: -0.1700
Data Index: 8501866 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.8546. Min Act: -0.1700
Data Index: 5354083 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.7921. Min Act: -0.1700
Data Index: 3300769 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.7609. Min Act: -0.1700
Data Index: 4836447 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.7296. Min Act: -0.1700
Data Index: 1197719 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.6359. Min Act: -0.1700
Data Index: 6123656 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.6359. Min Act: -0.1700
Data Index: 4407767 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.5734. Min Act: -0.1700
Data Index: 8739400 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.5734. Min Act: -0.1700
Data Index: 3806970 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.5421. Min Act: -0.1700
Data Index: 1816137 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.5109. Min Act: -0.1700
Data Index: 5615352 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.5109. Min Act: -0.1700
Data Index: 4856615 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.4796. Min Act: -0.1700
Data Index: 4905122 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.4796. Min Act: -0.1700
Data Index: 6307448 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.4796. Min Act: -0.1700
Data Index: 5626997 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.4796. Min Act: -0.1700
Data Index: 842985 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.4796. Min Act: -0.1700
Data Index: 60056 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1671. Min Range: -7.1671
Max Act: 6.4796. Min Act: -0.1700
Data Index: 5320613 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19