Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 564 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.6612. Min Act: -0.1700
Data Index: 3838298 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.4737. Min Act: -0.1700
Data Index: 1693159 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.4737. Min Act: -0.1700
Data Index: 4005834 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.2862. Min Act: -0.1700
Data Index: 1369173 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.2862. Min Act: -0.1700
Data Index: 3435531 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.2862. Min Act: -0.1700
Data Index: 6958443 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.2862. Min Act: -0.1700
Data Index: 6199391 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.2237. Min Act: -0.1700
Data Index: 6699471 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.1612. Min Act: -0.1700
Data Index: 2738371 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.2237. Min Act: -0.1700
Data Index: 6453984 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.1612. Min Act: -0.1700
Data Index: 6645232 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.1612. Min Act: -0.1700
Data Index: 4175374 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.2237. Min Act: -0.1700
Data Index: 4088528 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.1612. Min Act: -0.1700
Data Index: 8191384 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.1612. Min Act: -0.1700
Data Index: 6438358 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.0987. Min Act: -0.1700
Data Index: 7778023 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.1612. Min Act: -0.1700
Data Index: 5497663 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.1612. Min Act: -0.1700
Data Index: 5163353 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.0987. Min Act: -0.1700
Data Index: 2860953 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6612. Min Range: -9.6612
Max Act: 9.0987. Min Act: -0.1700
Data Index: 6619008 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19