Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 864 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1049. Min Range: -7.1049
Max Act: 7.1049. Min Act: -0.1700
Data Index: 6173640 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.7924. Min Act: -0.1700
Data Index: 6417588 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.7611. Min Act: -0.1700
Data Index: 2614593 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.7611. Min Act: -0.1700
Data Index: 7772826 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.7299. Min Act: -0.1700
Data Index: 6623088 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6986. Min Act: -0.1700
Data Index: 6105590 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6986. Min Act: -0.1700
Data Index: 4480595 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6986. Min Act: -0.1700
Data Index: 4150818 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6986. Min Act: -0.1700
Data Index: 5141698 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6986. Min Act: -0.1700
Data Index: 5783557 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6986. Min Act: -0.1700
Data Index: 8613898 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6674. Min Act: -0.1700
Data Index: 1145773 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6361. Min Act: -0.1700
Data Index: 2940343 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6674. Min Act: -0.1700
Data Index: 6662540 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6361. Min Act: -0.1700
Data Index: 3964485 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6361. Min Act: -0.1700
Data Index: 1659881 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6049. Min Act: -0.1700
Data Index: 6627494 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6361. Min Act: -0.1700
Data Index: 311262 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6049. Min Act: -0.1700
Data Index: 770359 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1049. Min Range: -7.1049
Max Act: 6.6049. Min Act: -0.1700
Data Index: 5937986 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19