Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 682 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1953. Min Range: -6.1953
Max Act: 6.1953. Min Act: -0.1700
Data Index: 7718888 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1953. Min Range: -6.1953
Max Act: 6.1328. Min Act: -0.1700
Data Index: 1347195 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1953. Min Range: -6.1953
Max Act: 6.0703. Min Act: -0.1700
Data Index: 6456787 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1953. Min Range: -6.1953
Max Act: 6.0078. Min Act: -0.1700
Data Index: 5626439 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.9140. Min Act: -0.1700
Data Index: 3586158 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.8515. Min Act: -0.1700
Data Index: 5505708 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.7890. Min Act: -0.1700
Data Index: 2015877 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.8515. Min Act: -0.1700
Data Index: 2731002 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.8203. Min Act: -0.1700
Data Index: 3570864 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.7890. Min Act: -0.1700
Data Index: 3663452 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.7890. Min Act: -0.1700
Data Index: 8623924 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.7265. Min Act: -0.1700
Data Index: 1306580 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.7578. Min Act: -0.1700
Data Index: 166175 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.7265. Min Act: -0.1700
Data Index: 4398949 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.6953. Min Act: -0.1700
Data Index: 2458007 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.7265. Min Act: -0.1700
Data Index: 4769017 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.6953. Min Act: -0.1700
Data Index: 3726752 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.6640. Min Act: -0.1700
Data Index: 7547893 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.6640. Min Act: -0.1700
Data Index: 2387313 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1953. Min Range: -6.1953
Max Act: 5.6640. Min Act: -0.1700
Data Index: 5546490 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19