Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.4009. Min Act: -0.1700
Data Index: 8040059 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.2911. Min Act: -0.1700
Data Index: 3381394 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.2754. Min Act: -0.1700
Data Index: 159468 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.2754. Min Act: -0.1700
Data Index: 8344367 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1496. Min Act: -0.1700
Data Index: 8166733 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1496. Min Act: -0.1700
Data Index: 5501498 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1653. Min Act: -0.1700
Data Index: 2207157 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1496. Min Act: -0.1700
Data Index: 6138054 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1496. Min Act: -0.1700
Data Index: 4326216 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1181. Min Act: -0.1700
Data Index: 7317511 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1339. Min Act: -0.1700
Data Index: 999841 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1181. Min Act: -0.1700
Data Index: 5483688 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1181. Min Act: -0.1700
Data Index: 104767 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1181. Min Act: -0.1700
Data Index: 505157 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1023. Min Act: -0.1700
Data Index: 742935 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1023. Min Act: -0.1700
Data Index: 6622288 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.0866. Min Act: -0.1700
Data Index: 7726971 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1023. Min Act: -0.1700
Data Index: 7115147 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1023. Min Act: -0.1700
Data Index: 4745215 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4009. Min Range: -3.4009
Max Act: 3.1181. Min Act: -0.1700
Data Index: 5652021 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19