Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 913 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.4263. Min Act: -0.1700
Data Index: 4047361 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.3793. Min Act: -0.1700
Data Index: 4127687 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.3636. Min Act: -0.1700
Data Index: 3850890 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.3165. Min Act: -0.1700
Data Index: 1773550 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.2694. Min Act: -0.1700
Data Index: 6978345 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.2694. Min Act: -0.1700
Data Index: 2455832 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.2537. Min Act: -0.1700
Data Index: 6426092 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.2537. Min Act: -0.1700
Data Index: 6513922 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.2537. Min Act: -0.1700
Data Index: 37368 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.2380. Min Act: -0.1700
Data Index: 4141184 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.2380. Min Act: -0.1700
Data Index: 5572283 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.2380. Min Act: -0.1700
Data Index: 7525375 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.1908. Min Act: -0.1700
Data Index: 3900441 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.1908. Min Act: -0.1700
Data Index: 1977138 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.1594. Min Act: -0.1700
Data Index: 5161949 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.1594. Min Act: -0.1700
Data Index: 4472037 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.1594. Min Act: -0.1700
Data Index: 2047365 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.1594. Min Act: -0.1700
Data Index: 6567472 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.1436. Min Act: -0.1700
Data Index: 7451691 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4263. Min Range: -3.4263
Max Act: 3.1436. Min Act: -0.1700
Data Index: 623062 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19