Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.5299. Min Act: -0.1700
Data Index: 8488985 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.4674. Min Act: -0.1700
Data Index: 790613 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.4674. Min Act: -0.1700
Data Index: 1733174 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.3424. Min Act: -0.1700
Data Index: 8214498 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.2486. Min Act: -0.1700
Data Index: 1827760 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.2799. Min Act: -0.1700
Data Index: 3677675 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.2174. Min Act: -0.1700
Data Index: 5929856 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.2174. Min Act: -0.1700
Data Index: 3158070 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.1861. Min Act: -0.1700
Data Index: 4532581 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.1549. Min Act: -0.1700
Data Index: 147717 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.1549. Min Act: -0.1700
Data Index: 5932613 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.1549. Min Act: -0.1700
Data Index: 2452159 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.1549. Min Act: -0.1700
Data Index: 4663661 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.1236. Min Act: -0.1700
Data Index: 3713402 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.1549. Min Act: -0.1700
Data Index: 718990 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.1236. Min Act: -0.1700
Data Index: 2463231 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.0924. Min Act: -0.1700
Data Index: 2454534 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.0924. Min Act: -0.1700
Data Index: 379904 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.0924. Min Act: -0.1700
Data Index: 78630 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5299. Min Range: -6.5299
Max Act: 6.0924. Min Act: -0.1700
Data Index: 2971441 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19