Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 896 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2319. Min Range: -9.2319
Max Act: 9.2319. Min Act: -0.1700
Data Index: 1811975 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2319. Min Range: -9.2319
Max Act: 9.2319. Min Act: -0.1700
Data Index: 3269652 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2319. Min Range: -9.2319
Max Act: 9.1069. Min Act: -0.1700
Data Index: 7434207 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2319. Min Range: -9.2319
Max Act: 9.0444. Min Act: -0.1700
Data Index: 2065480 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.9819. Min Act: -0.1700
Data Index: 8612063 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.8569. Min Act: -0.1700
Data Index: 6169755 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.7944. Min Act: -0.1700
Data Index: 7971181 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.8569. Min Act: -0.1700
Data Index: 806124 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.8569. Min Act: -0.1700
Data Index: 8717641 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.7944. Min Act: -0.1700
Data Index: 1933284 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.7319. Min Act: -0.1700
Data Index: 3061287 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.7319. Min Act: -0.1700
Data Index: 3705493 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.7319. Min Act: -0.1700
Data Index: 3380039 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.6069. Min Act: -0.1700
Data Index: 8084491 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.6694. Min Act: -0.1700
Data Index: 7520081 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.6069. Min Act: -0.1700
Data Index: 804427 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.6069. Min Act: -0.1700
Data Index: 7695859 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.6069. Min Act: -0.1700
Data Index: 3449706 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.6069. Min Act: -0.1700
Data Index: 4683236 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2319. Min Range: -9.2319
Max Act: 8.5444. Min Act: -0.1700
Data Index: 1527600 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19