Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5623 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.8179. Min Act: -0.1700
Data Index: 1605309 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.7554. Min Act: -0.1700
Data Index: 1597106 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.7554. Min Act: -0.1700
Data Index: 7384688 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.6304. Min Act: -0.1700
Data Index: 578214 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.6617. Min Act: -0.1700
Data Index: 399531 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.6304. Min Act: -0.1700
Data Index: 5128974 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.6304. Min Act: -0.1700
Data Index: 4726731 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.6304. Min Act: -0.1700
Data Index: 5744595 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.5992. Min Act: -0.1700
Data Index: 6846818 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.5992. Min Act: -0.1700
Data Index: 1263720 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.5992. Min Act: -0.1700
Data Index: 2863838 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.5679. Min Act: -0.1700
Data Index: 4409092 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.5367. Min Act: -0.1700
Data Index: 885995 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.5367. Min Act: -0.1700
Data Index: 711993 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.5054. Min Act: -0.1700
Data Index: 832616 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.5054. Min Act: -0.1700
Data Index: 6731881 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.5367. Min Act: -0.1700
Data Index: 8220515 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.5054. Min Act: -0.1700
Data Index: 4541461 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.5054. Min Act: -0.1700
Data Index: 6738123 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8179. Min Range: -4.8179
Max Act: 4.5054. Min Act: -0.1700
Data Index: 3761145 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19