Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 646 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0206. Min Range: -6.0206
Max Act: 6.0206. Min Act: -0.1700
Data Index: 706084 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.9893. Min Act: -0.1700
Data Index: 706071 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.8956. Min Act: -0.1700
Data Index: 7985819 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.8643. Min Act: -0.1700
Data Index: 397136 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.8331. Min Act: -0.1700
Data Index: 5728410 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.7706. Min Act: -0.1700
Data Index: 105004 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.7706. Min Act: -0.1700
Data Index: 8817270 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.7393. Min Act: -0.1700
Data Index: 5540429 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.7393. Min Act: -0.1700
Data Index: 2599035 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.7081. Min Act: -0.1700
Data Index: 3572846 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.6768. Min Act: -0.1700
Data Index: 1926933 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.6768. Min Act: -0.1700
Data Index: 5488059 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.6456. Min Act: -0.1700
Data Index: 6708282 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.6456. Min Act: -0.1700
Data Index: 5540430 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.6456. Min Act: -0.1700
Data Index: 8092232 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.6143. Min Act: -0.1700
Data Index: 6789792 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.6143. Min Act: -0.1700
Data Index: 2599900 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.6143. Min Act: -0.1700
Data Index: 6359993 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.6143. Min Act: -0.1700
Data Index: 5398636 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0206. Min Range: -6.0206
Max Act: 5.5831. Min Act: -0.1700
Data Index: 7291385 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19