Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0194. Min Range: -6.0194
Max Act: 6.0194. Min Act: -0.1700
Data Index: 7351151 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.7694. Min Act: -0.1700
Data Index: 7017690 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.7069. Min Act: -0.1700
Data Index: 8477196 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.7069. Min Act: -0.1700
Data Index: 2545242 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.6444. Min Act: -0.1700
Data Index: 5196143 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.6756. Min Act: -0.1700
Data Index: 4127953 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.6444. Min Act: -0.1700
Data Index: 8373318 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.6131. Min Act: -0.1700
Data Index: 1936301 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.6131. Min Act: -0.1700
Data Index: 2226241 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.6131. Min Act: -0.1700
Data Index: 8684487 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.5819. Min Act: -0.1700
Data Index: 6472701 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.6131. Min Act: -0.1700
Data Index: 2042743 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.6131. Min Act: -0.1700
Data Index: 7464227 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.5506. Min Act: -0.1700
Data Index: 3113596 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.5819. Min Act: -0.1700
Data Index: 8067637 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.6131. Min Act: -0.1700
Data Index: 2179279 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.5819. Min Act: -0.1700
Data Index: 6810874 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.5819. Min Act: -0.1700
Data Index: 2747190 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.5194. Min Act: -0.1700
Data Index: 5544702 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0194. Min Range: -6.0194
Max Act: 5.5194. Min Act: -0.1700
Data Index: 3265541 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19