Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2880 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.6985. Min Act: -0.1700
Data Index: 1437417 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.6673. Min Act: -0.1700
Data Index: 5397210 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.6360. Min Act: -0.1700
Data Index: 6707173 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.5735. Min Act: -0.1700
Data Index: 2954890 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.5423. Min Act: -0.1700
Data Index: 4676705 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.5110. Min Act: -0.1700
Data Index: 8212153 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.4485. Min Act: -0.1700
Data Index: 4665657 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.4485. Min Act: -0.1700
Data Index: 3169469 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.3860. Min Act: -0.1700
Data Index: 1335201 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.3548. Min Act: -0.1700
Data Index: 7700204 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.3235. Min Act: -0.1700
Data Index: 4010288 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.3235. Min Act: -0.1700
Data Index: 5053858 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.3548. Min Act: -0.1700
Data Index: 1387144 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.2923. Min Act: -0.1700
Data Index: 7238843 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.2923. Min Act: -0.1700
Data Index: 3524711 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.2298. Min Act: -0.1700
Data Index: 1789851 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.2298. Min Act: -0.1700
Data Index: 6058871 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.1673. Min Act: -0.1700
Data Index: 925512 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.1360. Min Act: -0.1700
Data Index: 6840806 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6985. Min Range: -6.6985
Max Act: 6.1360. Min Act: -0.1700
Data Index: 547464 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19