Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5876 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.4483. Min Range: -14.4483
Max Act: 14.4483. Min Act: -0.1700
Data Index: 284194 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.4483. Min Range: -14.4483
Max Act: 14.4483. Min Act: -0.1700
Data Index: 2009084 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.4483. Min Range: -14.4483
Max Act: 14.3233. Min Act: -0.1700
Data Index: 4130621 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.4483. Min Range: -14.4483
Max Act: 14.3233. Min Act: -0.1700
Data Index: 8684216 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.4483. Min Range: -14.4483
Max Act: 14.1358. Min Act: -0.1700
Data Index: 3954036 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.4483. Min Range: -14.4483
Max Act: 14.0108. Min Act: -0.1700
Data Index: 506493 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.4483. Min Range: -14.4483
Max Act: 13.8858. Min Act: -0.1700
Data Index: 4970961 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.4483. Min Range: -14.4483
Max Act: 13.9483. Min Act: -0.1700
Data Index: 7549154 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.4483. Min Range: -14.4483
Max Act: 13.9483. Min Act: -0.1700
Data Index: 4272956 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.4483. Min Range: -14.4483
Max Act: 13.9483. Min Act: -0.1700
Data Index: 8097874 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.4483. Min Range: -14.4483
Max Act: 13.8858. Min Act: -0.1700
Data Index: 6403792 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.4483. Min Range: -14.4483
Max Act: 13.8858. Min Act: -0.1700
Data Index: 2044207 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.4483. Min Range: -14.4483
Max Act: 13.8233. Min Act: -0.1700
Data Index: 6910706 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.4483. Min Range: -14.4483
Max Act: 13.8233. Min Act: -0.1700
Data Index: 2884154 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.4483. Min Range: -14.4483
Max Act: 13.8233. Min Act: -0.1700
Data Index: 5884418 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.4483. Min Range: -14.4483
Max Act: 13.8858. Min Act: -0.1700
Data Index: 980880 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.4483. Min Range: -14.4483
Max Act: 13.8233. Min Act: -0.1700
Data Index: 4572310 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.4483. Min Range: -14.4483
Max Act: 13.7608. Min Act: -0.1700
Data Index: 6409235 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.4483. Min Range: -14.4483
Max Act: 13.6983. Min Act: -0.1700
Data Index: 3196287 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.4483. Min Range: -14.4483
Max Act: 13.7608. Min Act: -0.1700
Data Index: 8492832 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19