Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1607 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.6093. Min Act: -0.1700
Data Index: 5078940 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.4530. Min Act: -0.1700
Data Index: 998599 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.4218. Min Act: -0.1700
Data Index: 5775563 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.4530. Min Act: -0.1700
Data Index: 6525552 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.3905. Min Act: -0.1700
Data Index: 6525553 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.3593. Min Act: -0.1700
Data Index: 1177572 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.3593. Min Act: -0.1700
Data Index: 4798600 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.3593. Min Act: -0.1700
Data Index: 170895 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.3593. Min Act: -0.1700
Data Index: 8245450 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.3280. Min Act: -0.1700
Data Index: 7521354 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.3280. Min Act: -0.1700
Data Index: 8566796 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.2655. Min Act: -0.1700
Data Index: 2872751 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.2968. Min Act: -0.1700
Data Index: 4338091 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.2655. Min Act: -0.1700
Data Index: 21524 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.2655. Min Act: -0.1700
Data Index: 2089092 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.2030. Min Act: -0.1700
Data Index: 4406239 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.2343. Min Act: -0.1700
Data Index: 6525554 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.2030. Min Act: -0.1700
Data Index: 3063923 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.2343. Min Act: -0.1700
Data Index: 1673157 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.2343. Min Act: -0.1700
Data Index: 8272076 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19