Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4293 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.9169. Min Act: -0.1700
Data Index: 1934551 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.7605. Min Act: -0.1700
Data Index: 8527264 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.4788. Min Act: -0.1700
Data Index: 2232792 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.4475. Min Act: -0.1700
Data Index: 1680743 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.4318. Min Act: -0.1700
Data Index: 2311011 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.4318. Min Act: -0.1700
Data Index: 5458743 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.4475. Min Act: -0.1700
Data Index: 2407058 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.4005. Min Act: -0.1700
Data Index: 730944 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.4162. Min Act: -0.1700
Data Index: 822813 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.3848. Min Act: -0.1700
Data Index: 547253 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.3848. Min Act: -0.1700
Data Index: 6955456 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.3534. Min Act: -0.1700
Data Index: 1032923 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.3377. Min Act: -0.1700
Data Index: 1018446 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.3220. Min Act: -0.1700
Data Index: 2626295 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.3377. Min Act: -0.1700
Data Index: 7478429 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.3220. Min Act: -0.1700
Data Index: 2320594 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.3220. Min Act: -0.1700
Data Index: 827508 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.3220. Min Act: -0.1700
Data Index: 7946224 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.3220. Min Act: -0.1700
Data Index: 2362596 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9169. Min Range: -3.9169
Max Act: 3.3064. Min Act: -0.1700
Data Index: 5683031 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19