Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.8793. Min Act: -0.1700
Data Index: 4968419 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.7230. Min Act: -0.1700
Data Index: 6345083 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.6448. Min Act: -0.1700
Data Index: 2586076 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.6291. Min Act: -0.1700
Data Index: 6855238 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.6135. Min Act: -0.1700
Data Index: 5614109 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.5352. Min Act: -0.1700
Data Index: 2380541 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.5195. Min Act: -0.1700
Data Index: 3176880 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.5039. Min Act: -0.1700
Data Index: 7299181 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.5039. Min Act: -0.1700
Data Index: 2320774 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.5039. Min Act: -0.1700
Data Index: 8538462 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.4882. Min Act: -0.1700
Data Index: 3295697 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.4882. Min Act: -0.1700
Data Index: 7576887 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.4569. Min Act: -0.1700
Data Index: 1339914 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.4725. Min Act: -0.1700
Data Index: 6891358 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.4412. Min Act: -0.1700
Data Index: 3220196 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.4099. Min Act: -0.1700
Data Index: 1946864 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.4255. Min Act: -0.1700
Data Index: 7647249 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.4255. Min Act: -0.1700
Data Index: 8697751 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.4099. Min Act: -0.1700
Data Index: 1148917 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8793. Min Range: -3.8793
Max Act: 3.4099. Min Act: -0.1700
Data Index: 7401297 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19