Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2991 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.8683. Min Act: -0.1700
Data Index: 4836166 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.5245. Min Act: -0.1700
Data Index: 708968 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.4308. Min Act: -0.1700
Data Index: 8695202 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.2120. Min Act: -0.1700
Data Index: 6807311 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.2120. Min Act: -0.1700
Data Index: 1780644 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.1495. Min Act: -0.1700
Data Index: 1780653 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.0870. Min Act: -0.1700
Data Index: 429082 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.0870. Min Act: -0.1700
Data Index: 8043120 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.0558. Min Act: -0.1700
Data Index: 2540511 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.0558. Min Act: -0.1700
Data Index: 4370393 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8683. Min Range: -6.8683
Max Act: 6.0245. Min Act: -0.1700
Data Index: 2392986 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8683. Min Range: -6.8683
Max Act: 5.9933. Min Act: -0.1700
Data Index: 2769392 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8683. Min Range: -6.8683
Max Act: 5.9933. Min Act: -0.1700
Data Index: 1541486 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8683. Min Range: -6.8683
Max Act: 5.9620. Min Act: -0.1700
Data Index: 1452428 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8683. Min Range: -6.8683
Max Act: 5.9620. Min Act: -0.1700
Data Index: 40607 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8683. Min Range: -6.8683
Max Act: 5.9620. Min Act: -0.1700
Data Index: 2690494 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8683. Min Range: -6.8683
Max Act: 5.9308. Min Act: -0.1700
Data Index: 8158844 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8683. Min Range: -6.8683
Max Act: 5.9308. Min Act: -0.1700
Data Index: 6334560 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8683. Min Range: -6.8683
Max Act: 5.9308. Min Act: -0.1700
Data Index: 6923350 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8683. Min Range: -6.8683
Max Act: 5.9308. Min Act: -0.1700
Data Index: 7890385 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19