Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 713 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3862. Min Range: -9.3862
Max Act: 9.3862. Min Act: -0.1700
Data Index: 4930631 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3862. Min Range: -9.3862
Max Act: 9.0112. Min Act: -0.1700
Data Index: 3829437 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.7612. Min Act: -0.1700
Data Index: 251449 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.7612. Min Act: -0.1700
Data Index: 7267844 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.6987. Min Act: -0.1700
Data Index: 3121450 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.6362. Min Act: -0.1700
Data Index: 931500 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.6362. Min Act: -0.1700
Data Index: 3096967 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.5737. Min Act: -0.1700
Data Index: 1876434 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.5737. Min Act: -0.1700
Data Index: 1202968 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.5112. Min Act: -0.1700
Data Index: 2970575 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.5112. Min Act: -0.1700
Data Index: 8208320 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.4487. Min Act: -0.1700
Data Index: 401283 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.4487. Min Act: -0.1700
Data Index: 172899 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.3862. Min Act: -0.1700
Data Index: 1278355 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.3862. Min Act: -0.1700
Data Index: 575305 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.3862. Min Act: -0.1700
Data Index: 2925028 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.3862. Min Act: -0.1700
Data Index: 3818695 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.3862. Min Act: -0.1700
Data Index: 4894859 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.3862. Min Act: -0.1700
Data Index: 4320592 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3862. Min Range: -9.3862
Max Act: 8.3862. Min Act: -0.1700
Data Index: 5036138 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19