Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2616 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.5301. Min Act: -0.1700
Data Index: 4776182 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.5139. Min Act: -0.1700
Data Index: 84274 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.5139. Min Act: -0.1700
Data Index: 6650191 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4977. Min Act: -0.1700
Data Index: 7235301 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4815. Min Act: -0.1700
Data Index: 7108995 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4815. Min Act: -0.1700
Data Index: 5393360 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4815. Min Act: -0.1700
Data Index: 1598772 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4653. Min Act: -0.1700
Data Index: 6952045 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4653. Min Act: -0.1700
Data Index: 5989162 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4490. Min Act: -0.1700
Data Index: 6881862 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4490. Min Act: -0.1700
Data Index: 2714362 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4490. Min Act: -0.1700
Data Index: 3865588 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4490. Min Act: -0.1700
Data Index: 131763 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4490. Min Act: -0.1700
Data Index: 2870023 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4490. Min Act: -0.1700
Data Index: 2401809 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4328. Min Act: -0.1700
Data Index: 5476058 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4328. Min Act: -0.1700
Data Index: 5393375 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4328. Min Act: -0.1700
Data Index: 6321586 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4328. Min Act: -0.1700
Data Index: 5393364 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5301. Min Range: -2.5301
Max Act: 2.4328. Min Act: -0.1700
Data Index: 1814008 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19