Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1134 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.9362. Min Act: -0.1700
Data Index: 6020466 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8737. Min Act: -0.1700
Data Index: 7919253 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8737. Min Act: -0.1700
Data Index: 5362069 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8737. Min Act: -0.1700
Data Index: 5186476 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8737. Min Act: -0.1699
Data Index: 4322020 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8737. Min Act: -0.1700
Data Index: 4252474 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8737. Min Act: -0.1700
Data Index: 8649337 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8737. Min Act: -0.1700
Data Index: 8583980 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8737. Min Act: -0.1700
Data Index: 8523392 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8737. Min Act: -0.1700
Data Index: 1879896 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8737. Min Act: -0.1700
Data Index: 1414802 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8737. Min Act: -0.1699
Data Index: 7671551 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8424. Min Act: -0.1700
Data Index: 2866133 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8424. Min Act: -0.1700
Data Index: 3836508 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8424. Min Act: -0.1700
Data Index: 4101001 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8424. Min Act: -0.1699
Data Index: 4123433 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8424. Min Act: -0.1700
Data Index: 4412311 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8424. Min Act: -0.1700
Data Index: 4458866 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8424. Min Act: -0.1700
Data Index: 4845217 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9362. Min Range: -3.9362
Max Act: 3.8424. Min Act: -0.1700
Data Index: 761670 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19