Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1816 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.5257. Min Act: -0.1700
Data Index: 4510955 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.4944. Min Act: -0.1700
Data Index: 815249 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.4944. Min Act: -0.1700
Data Index: 6469988 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.4319. Min Act: -0.1700
Data Index: 1045302 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.4319. Min Act: -0.1700
Data Index: 4124468 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.4319. Min Act: -0.1700
Data Index: 8389369 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.3694. Min Act: -0.1700
Data Index: 8361869 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.2444. Min Act: -0.1700
Data Index: 7536511 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.2757. Min Act: -0.1700
Data Index: 8829583 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.2444. Min Act: -0.1700
Data Index: 7116619 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.2444. Min Act: -0.1700
Data Index: 6383464 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.2444. Min Act: -0.1700
Data Index: 3958749 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.2132. Min Act: -0.1700
Data Index: 7667228 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.2132. Min Act: -0.1700
Data Index: 2917116 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.2132. Min Act: -0.1700
Data Index: 7711189 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.2132. Min Act: -0.1700
Data Index: 7663884 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.2132. Min Act: -0.1700
Data Index: 8123361 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.1819. Min Act: -0.1700
Data Index: 8649125 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.1819. Min Act: -0.1700
Data Index: 3157602 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5257. Min Range: -6.5257
Max Act: 6.1819. Min Act: -0.1700
Data Index: 8450096 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19