Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2458 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.6507. Min Act: -0.1700
Data Index: 3563699 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.5569. Min Act: -0.1700
Data Index: 6958066 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.5257. Min Act: -0.1700
Data Index: 1940929 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.4944. Min Act: -0.1700
Data Index: 3585399 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.4632. Min Act: -0.1700
Data Index: 3563701 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.4319. Min Act: -0.1700
Data Index: 5730819 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.4319. Min Act: -0.1700
Data Index: 6417756 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.4007. Min Act: -0.1700
Data Index: 1649749 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.4319. Min Act: -0.1700
Data Index: 1967275 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.4007. Min Act: -0.1700
Data Index: 1614695 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.3694. Min Act: -0.1700
Data Index: 3769777 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.3694. Min Act: -0.1700
Data Index: 8409787 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.3382. Min Act: -0.1700
Data Index: 5492064 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.3382. Min Act: -0.1700
Data Index: 1838914 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.3382. Min Act: -0.1700
Data Index: 3896957 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.3382. Min Act: -0.1699
Data Index: 1181846 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.3382. Min Act: -0.1700
Data Index: 6245299 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.3382. Min Act: -0.1700
Data Index: 6281696 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.3382. Min Act: -0.1700
Data Index: 2221088 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6507. Min Range: -5.6507
Max Act: 5.3069. Min Act: -0.1699
Data Index: 6586053 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19