Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5589 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0215. Min Range: -4.0215
Max Act: 4.0215. Min Act: -0.1700
Data Index: 4152155 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.9903. Min Act: -0.1700
Data Index: 602007 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.9590. Min Act: -0.1700
Data Index: 1790165 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.9278. Min Act: -0.1700
Data Index: 1152127 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.9278. Min Act: -0.1700
Data Index: 7076727 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.9278. Min Act: -0.1700
Data Index: 3333647 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.9278. Min Act: -0.1700
Data Index: 3214462 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.9278. Min Act: -0.1700
Data Index: 7672493 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.9278. Min Act: -0.1700
Data Index: 1790161 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.9278. Min Act: -0.1700
Data Index: 4336659 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.8965. Min Act: -0.1700
Data Index: 5521347 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.8965. Min Act: -0.1700
Data Index: 5521348 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.8965. Min Act: -0.1700
Data Index: 3214461 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.8965. Min Act: -0.1700
Data Index: 5570035 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.8965. Min Act: -0.1700
Data Index: 5929419 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.8965. Min Act: -0.1700
Data Index: 5614 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.8965. Min Act: -0.1700
Data Index: 6335148 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.8965. Min Act: -0.1700
Data Index: 527731 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.8965. Min Act: -0.1700
Data Index: 3201414 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0215. Min Range: -4.0215
Max Act: 3.8965. Min Act: -0.1700
Data Index: 1640517 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19