Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3336 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0849. Min Range: -6.0849
Max Act: 6.0849. Min Act: -0.1700
Data Index: 5327028 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0849. Min Range: -6.0849
Max Act: 6.0224. Min Act: -0.1700
Data Index: 6949476 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0849. Min Range: -6.0849
Max Act: 6.0224. Min Act: -0.1700
Data Index: 4987808 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.9911. Min Act: -0.1700
Data Index: 6644042 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.9599. Min Act: -0.1700
Data Index: 4514767 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.9599. Min Act: -0.1700
Data Index: 4666076 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.9599. Min Act: -0.1700
Data Index: 7267511 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.9286. Min Act: -0.1700
Data Index: 6012615 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.9286. Min Act: -0.1700
Data Index: 6921573 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.9286. Min Act: -0.1700
Data Index: 1417075 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.9286. Min Act: -0.1700
Data Index: 4949953 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.8974. Min Act: -0.1700
Data Index: 847524 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.8974. Min Act: -0.1700
Data Index: 4917036 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.8974. Min Act: -0.1700
Data Index: 7614336 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.8974. Min Act: -0.1700
Data Index: 4181511 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.8661. Min Act: -0.1700
Data Index: 1383210 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.8661. Min Act: -0.1700
Data Index: 6759489 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.8661. Min Act: -0.1700
Data Index: 292932 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.8349. Min Act: -0.1700
Data Index: 2787429 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0849. Min Range: -6.0849
Max Act: 5.8661. Min Act: -0.1700
Data Index: 3803643 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19