Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5459 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.9240. Min Act: -0.1700
Data Index: 5585981 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.7365. Min Act: -0.1700
Data Index: 2223332 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.6115. Min Act: -0.1700
Data Index: 8569763 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.4865. Min Act: -0.1700
Data Index: 7774077 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.4865. Min Act: -0.1700
Data Index: 3770707 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.3615. Min Act: -0.1700
Data Index: 1592864 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.2990. Min Act: -0.1700
Data Index: 2960407 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.2990. Min Act: -0.1700
Data Index: 961816 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.2990. Min Act: -0.1700
Data Index: 4367049 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.2365. Min Act: -0.1700
Data Index: 5423090 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.2365. Min Act: -0.1700
Data Index: 8569764 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.1740. Min Act: -0.1700
Data Index: 3201776 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.1115. Min Act: -0.1700
Data Index: 6073273 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.1115. Min Act: -0.1700
Data Index: 5833682 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.0490. Min Act: -0.1700
Data Index: 1230497 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.1115. Min Act: -0.1700
Data Index: 4203382 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.0490. Min Act: -0.1700
Data Index: 6693321 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9240. Min Range: -9.9240
Max Act: 9.0490. Min Act: -0.1700
Data Index: 3177876 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9240. Min Range: -9.9240
Max Act: 8.9240. Min Act: -0.1700
Data Index: 5421346 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9240. Min Range: -9.9240
Max Act: 8.9865. Min Act: -0.1700
Data Index: 770262 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19