Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2116 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6961. Min Range: -7.6961
Max Act: 7.6961. Min Act: -0.1700
Data Index: 506611 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6961. Min Range: -7.6961
Max Act: 7.1649. Min Act: -0.1700
Data Index: 388580 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6961. Min Range: -7.6961
Max Act: 7.0399. Min Act: -0.1700
Data Index: 1489788 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.9774. Min Act: -0.1700
Data Index: 7348096 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.9774. Min Act: -0.1700
Data Index: 5885276 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.9461. Min Act: -0.1700
Data Index: 6727923 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.8836. Min Act: -0.1700
Data Index: 3360383 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.8836. Min Act: -0.1700
Data Index: 745311 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.8524. Min Act: -0.1700
Data Index: 6499909 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.8524. Min Act: -0.1700
Data Index: 1259310 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.8524. Min Act: -0.1700
Data Index: 2756751 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.8211. Min Act: -0.1700
Data Index: 6473794 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.6649. Min Act: -0.1700
Data Index: 7756240 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.6649. Min Act: -0.1700
Data Index: 2252879 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.6649. Min Act: -0.1700
Data Index: 2552098 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.6336. Min Act: -0.1700
Data Index: 5346153 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.6024. Min Act: -0.1700
Data Index: 576059 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.6336. Min Act: -0.1700
Data Index: 559133 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.5711. Min Act: -0.1700
Data Index: 4037367 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6961. Min Range: -7.6961
Max Act: 6.5711. Min Act: -0.1700
Data Index: 8101244 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19