Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2849 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.6307. Min Act: -0.1700
Data Index: 1875284 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.6307. Min Act: -0.1700
Data Index: 7205721 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.5681. Min Act: -0.1700
Data Index: 1718323 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.5211. Min Act: -0.1700
Data Index: 4749523 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.5211. Min Act: -0.1700
Data Index: 6235064 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.5211. Min Act: -0.1700
Data Index: 7160607 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.5055. Min Act: -0.1700
Data Index: 953502 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.5055. Min Act: -0.1700
Data Index: 4203105 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.4898. Min Act: -0.1700
Data Index: 3512444 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.4898. Min Act: -0.1700
Data Index: 4482727 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.4898. Min Act: -0.1700
Data Index: 3048969 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.4741. Min Act: -0.1700
Data Index: 2348525 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.4741. Min Act: -0.1700
Data Index: 8021943 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.4741. Min Act: -0.1700
Data Index: 1705306 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.4741. Min Act: -0.1700
Data Index: 8430690 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.4585. Min Act: -0.1700
Data Index: 3336685 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.4585. Min Act: -0.1700
Data Index: 6255649 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.4585. Min Act: -0.1700
Data Index: 902513 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.4428. Min Act: -0.1700
Data Index: 367436 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6307. Min Range: -3.6307
Max Act: 3.4428. Min Act: -0.1700
Data Index: 583742 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19