Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.5036. Min Act: -0.1700
Data Index: 7027780 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.4724. Min Act: -0.1700
Data Index: 1131159 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3786. Min Act: -0.1700
Data Index: 7993340 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3474. Min Act: -0.1700
Data Index: 5619217 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3474. Min Act: -0.1700
Data Index: 2600501 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3161. Min Act: -0.1700
Data Index: 3423781 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3161. Min Act: -0.1700
Data Index: 6976324 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3161. Min Act: -0.1700
Data Index: 3719204 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3161. Min Act: -0.1700
Data Index: 5310729 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3161. Min Act: -0.1700
Data Index: 2069462 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3161. Min Act: -0.1700
Data Index: 7018562 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.2848. Min Act: -0.1700
Data Index: 7763582 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.2223. Min Act: -0.1700
Data Index: 1348960 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.2223. Min Act: -0.1700
Data Index: 4709956 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.2223. Min Act: -0.1700
Data Index: 6489772 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.2223. Min Act: -0.1700
Data Index: 8446673 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.1911. Min Act: -0.1700
Data Index: 1443474 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.1911. Min Act: -0.1700
Data Index: 5644641 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.1911. Min Act: -0.1700
Data Index: 6818170 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.1598. Min Act: -0.1700
Data Index: 1070893 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19