Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1831 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.5380. Min Act: -0.1700
Data Index: 1031189 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.3818. Min Act: -0.1700
Data Index: 5809 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.3818. Min Act: -0.1700
Data Index: 5437528 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.3505. Min Act: -0.1700
Data Index: 550288 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.3505. Min Act: -0.1700
Data Index: 548519 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.3818. Min Act: -0.1700
Data Index: 3729710 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.3505. Min Act: -0.1700
Data Index: 8141321 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.3193. Min Act: -0.1700
Data Index: 4672951 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.2880. Min Act: -0.1700
Data Index: 3520365 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.2568. Min Act: -0.1700
Data Index: 4192087 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.2880. Min Act: -0.1700
Data Index: 7262766 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.2880. Min Act: -0.1700
Data Index: 140020 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.2880. Min Act: -0.1700
Data Index: 6548803 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.2880. Min Act: -0.1700
Data Index: 403398 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.2880. Min Act: -0.1700
Data Index: 1172165 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.2568. Min Act: -0.1700
Data Index: 5194455 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.2255. Min Act: -0.1700
Data Index: 2576756 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.2568. Min Act: -0.1700
Data Index: 768250 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.2255. Min Act: -0.1700
Data Index: 779014 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5380. Min Range: -5.5380
Max Act: 5.2255. Min Act: -0.1700
Data Index: 5335978 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19