Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.8307. Min Act: -0.1700
Data Index: 5177727 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.7056. Min Act: -0.1700
Data Index: 3852807 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.5804. Min Act: -0.1700
Data Index: 5177729 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.6117. Min Act: -0.1700
Data Index: 6514237 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.6117. Min Act: -0.1700
Data Index: 4795536 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.6117. Min Act: -0.1700
Data Index: 5479238 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.6117. Min Act: -0.1700
Data Index: 5177728 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.6117. Min Act: -0.1700
Data Index: 3538607 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.5491. Min Act: -0.1700
Data Index: 5177730 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.5491. Min Act: -0.1700
Data Index: 1291371 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.5491. Min Act: -0.1700
Data Index: 309182 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.5178. Min Act: -0.1700
Data Index: 337692 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.5178. Min Act: -0.1700
Data Index: 7666779 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.4864. Min Act: -0.1700
Data Index: 4319888 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.4864. Min Act: -0.1700
Data Index: 1141994 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.4864. Min Act: -0.1700
Data Index: 4922812 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.4864. Min Act: -0.1700
Data Index: 5740306 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.4864. Min Act: -0.1700
Data Index: 2633170 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.4864. Min Act: -0.1700
Data Index: 4951959 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.4864. Min Act: -0.1700
Data Index: 7428590 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19