Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1718 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.7768. Min Act: -0.1700
Data Index: 5401059 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.7768. Min Act: -0.1700
Data Index: 4507600 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.6831. Min Act: -0.1700
Data Index: 5649468 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.6831. Min Act: -0.1700
Data Index: 5810749 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.5581. Min Act: -0.1700
Data Index: 5643349 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.5268. Min Act: -0.1700
Data Index: 250089 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.5581. Min Act: -0.1700
Data Index: 5100538 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.5268. Min Act: -0.1700
Data Index: 7761432 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.4956. Min Act: -0.1700
Data Index: 5135879 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.4643. Min Act: -0.1700
Data Index: 6852455 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.4331. Min Act: -0.1700
Data Index: 6545799 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.3706. Min Act: -0.1700
Data Index: 3446450 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.4018. Min Act: -0.1700
Data Index: 4231023 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.4018. Min Act: -0.1700
Data Index: 7279053 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.3393. Min Act: -0.1700
Data Index: 3277273 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.3393. Min Act: -0.1700
Data Index: 2671518 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.3081. Min Act: -0.1700
Data Index: 7777831 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.3081. Min Act: -0.1700
Data Index: 7361826 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.3081. Min Act: -0.1700
Data Index: 6891215 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7768. Min Range: -5.7768
Max Act: 5.2768. Min Act: -0.1700
Data Index: 5994253 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19