Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2506 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.4445. Min Act: -0.1700
Data Index: 5814652 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3818. Min Act: -0.1700
Data Index: 5180191 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3974. Min Act: -0.1700
Data Index: 5859082 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3818. Min Act: -0.1700
Data Index: 7948441 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3818. Min Act: -0.1700
Data Index: 2974420 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3818. Min Act: -0.1700
Data Index: 8102285 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3661. Min Act: -0.1700
Data Index: 2515838 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3661. Min Act: -0.1700
Data Index: 354786 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3661. Min Act: -0.1700
Data Index: 4780554 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3661. Min Act: -0.1700
Data Index: 4767599 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3661. Min Act: -0.1700
Data Index: 8329720 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3661. Min Act: -0.1700
Data Index: 5030574 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3504. Min Act: -0.1700
Data Index: 4900486 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3504. Min Act: -0.1700
Data Index: 955102 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3504. Min Act: -0.1700
Data Index: 7971747 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3504. Min Act: -0.1700
Data Index: 1733279 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3504. Min Act: -0.1700
Data Index: 5778733 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3504. Min Act: -0.1700
Data Index: 7947229 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3347. Min Act: -0.1700
Data Index: 5973116 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4445. Min Range: -3.4445
Max Act: 3.3347. Min Act: -0.1700
Data Index: 6441280 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19