Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 422 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3545. Min Range: -9.3545
Max Act: 9.3545. Min Act: -0.1700
Data Index: 6439857 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3545. Min Range: -9.3545
Max Act: 9.2920. Min Act: -0.1700
Data Index: 3509520 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.7920. Min Act: -0.1700
Data Index: 959342 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.7295. Min Act: -0.1700
Data Index: 8698163 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.6670. Min Act: -0.1700
Data Index: 5862538 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.4795. Min Act: -0.1700
Data Index: 1778480 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.3545. Min Act: -0.1700
Data Index: 3449189 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.3545. Min Act: -0.1700
Data Index: 7904340 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.2920. Min Act: -0.1700
Data Index: 6587160 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.2920. Min Act: -0.1700
Data Index: 2566650 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.2920. Min Act: -0.1700
Data Index: 6466381 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.2295. Min Act: -0.1700
Data Index: 7795281 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.2295. Min Act: -0.1700
Data Index: 4640297 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.1670. Min Act: -0.1700
Data Index: 4690632 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.1670. Min Act: -0.1700
Data Index: 635748 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.1670. Min Act: -0.1700
Data Index: 8571193 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.1045. Min Act: -0.1700
Data Index: 1974100 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.1045. Min Act: -0.1700
Data Index: 3994412 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.1045. Min Act: -0.1700
Data Index: 8272467 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3545. Min Range: -9.3545
Max Act: 8.1045. Min Act: -0.1700
Data Index: 1752695 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19