Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5340 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.7495. Min Act: -0.1700
Data Index: 740880 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.5932. Min Act: -0.1700
Data Index: 5745816 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.5932. Min Act: -0.1700
Data Index: 8193668 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.5932. Min Act: -0.1700
Data Index: 1368818 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.5307. Min Act: -0.1700
Data Index: 4333360 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.5307. Min Act: -0.1700
Data Index: 686239 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.5932. Min Act: -0.1700
Data Index: 2593601 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.5307. Min Act: -0.1700
Data Index: 3253141 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.5307. Min Act: -0.1700
Data Index: 2036432 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.5307. Min Act: -0.1700
Data Index: 1481585 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.5307. Min Act: -0.1700
Data Index: 654327 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.5307. Min Act: -0.1700
Data Index: 3586649 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.5307. Min Act: -0.1700
Data Index: 2475151 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.5307. Min Act: -0.1700
Data Index: 8105842 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.4995. Min Act: -0.1700
Data Index: 5355635 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.4995. Min Act: -0.1700
Data Index: 8163014 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.4995. Min Act: -0.1700
Data Index: 6283625 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.5307. Min Act: -0.1700
Data Index: 3157585 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.4682. Min Act: -0.1700
Data Index: 5796902 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7495. Min Range: -5.7495
Max Act: 5.4995. Min Act: -0.1700
Data Index: 2690756 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19