Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.2241. Min Act: -0.1698
Data Index: 4949578 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.2241. Min Act: -0.1700
Data Index: 4723146 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.1454. Min Act: -0.1700
Data Index: 1854786 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.1297. Min Act: -0.1700
Data Index: 3141694 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.1139. Min Act: -0.1700
Data Index: 8805586 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0982. Min Act: -0.1700
Data Index: 6444885 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0824. Min Act: -0.1700
Data Index: 5144091 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0666. Min Act: -0.1700
Data Index: 2621089 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0509. Min Act: -0.1700
Data Index: 1387619 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0509. Min Act: -0.1700
Data Index: 7348395 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0509. Min Act: -0.1700
Data Index: 5373102 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0351. Min Act: -0.1700
Data Index: 2909312 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0509. Min Act: -0.1700
Data Index: 3046055 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0351. Min Act: -0.1700
Data Index: 5567351 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0351. Min Act: -0.1700
Data Index: 1292062 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0193. Min Act: -0.1697
Data Index: 4138596 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0193. Min Act: -0.1700
Data Index: 1933546 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0035. Min Act: -0.1700
Data Index: 1695268 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0035. Min Act: -0.1700
Data Index: 7450508 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2241. Min Range: -3.2241
Max Act: 3.0035. Min Act: -0.1700
Data Index: 4578180 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19