Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2564 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8985. Min Act: -0.1700
Data Index: 2383960 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8668. Min Act: -0.1700
Data Index: 5563605 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8668. Min Act: -0.1700
Data Index: 4902149 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8509. Min Act: -0.1700
Data Index: 1004961 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8350. Min Act: -0.1700
Data Index: 5794906 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8350. Min Act: -0.1700
Data Index: 7187492 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8350. Min Act: -0.1700
Data Index: 7225733 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8350. Min Act: -0.1700
Data Index: 2136868 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8350. Min Act: -0.1700
Data Index: 2400406 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8350. Min Act: -0.1700
Data Index: 1944022 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8350. Min Act: -0.1700
Data Index: 5453298 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8350. Min Act: -0.1700
Data Index: 5543518 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8191. Min Act: -0.1700
Data Index: 5741857 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8191. Min Act: -0.1700
Data Index: 3711991 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8191. Min Act: -0.1700
Data Index: 5940462 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8191. Min Act: -0.1700
Data Index: 7636527 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8191. Min Act: -0.1700
Data Index: 8423115 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8032. Min Act: -0.1700
Data Index: 2803288 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8032. Min Act: -0.1700
Data Index: 258097 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8985. Min Range: -2.8985
Max Act: 2.8032. Min Act: -0.1700
Data Index: 2697995 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19