Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4296 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0656. Min Range: -8.0656
Max Act: 8.0656. Min Act: -0.1700
Data Index: 758714 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.8781. Min Act: -0.1700
Data Index: 3780671 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.8781. Min Act: -0.1700
Data Index: 6705623 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.8781. Min Act: -0.1700
Data Index: 1383245 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.8156. Min Act: -0.1700
Data Index: 3352429 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.7531. Min Act: -0.1700
Data Index: 7674154 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.7531. Min Act: -0.1700
Data Index: 2947029 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.8156. Min Act: -0.1700
Data Index: 4324798 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.7531. Min Act: -0.1700
Data Index: 2914698 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.7531. Min Act: -0.1700
Data Index: 7458834 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.6906. Min Act: -0.1700
Data Index: 8675291 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.6906. Min Act: -0.1700
Data Index: 6205454 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.5968. Min Act: -0.1700
Data Index: 2245223 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.6281. Min Act: -0.1700
Data Index: 3622461 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.5656. Min Act: -0.1700
Data Index: 3746763 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.5968. Min Act: -0.1700
Data Index: 809299 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.5656. Min Act: -0.1700
Data Index: 8505453 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.5968. Min Act: -0.1700
Data Index: 8516512 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.5968. Min Act: -0.1700
Data Index: 2536479 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0656. Min Range: -8.0656
Max Act: 7.5656. Min Act: -0.1700
Data Index: 1198874 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19