Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2193 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1868. Min Range: -7.1868
Max Act: 7.1868. Min Act: -0.1700
Data Index: 7982080 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1868. Min Range: -7.1868
Max Act: 7.0930. Min Act: -0.1700
Data Index: 2641897 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1868. Min Range: -7.1868
Max Act: 7.0618. Min Act: -0.1700
Data Index: 4372226 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.9993. Min Act: -0.1700
Data Index: 6283766 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.8118. Min Act: -0.1700
Data Index: 2089912 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.6555. Min Act: -0.1700
Data Index: 6794731 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.6868. Min Act: -0.1700
Data Index: 5872957 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.6555. Min Act: -0.1700
Data Index: 458792 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.5930. Min Act: -0.1700
Data Index: 7925877 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.4993. Min Act: -0.1700
Data Index: 2121984 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.4993. Min Act: -0.1700
Data Index: 3254710 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.4993. Min Act: -0.1700
Data Index: 191761 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.4680. Min Act: -0.1700
Data Index: 5599808 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.4368. Min Act: -0.1700
Data Index: 170954 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.4680. Min Act: -0.1700
Data Index: 1639033 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.4368. Min Act: -0.1700
Data Index: 166968 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.4368. Min Act: -0.1700
Data Index: 5262795 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.4368. Min Act: -0.1699
Data Index: 6602682 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.4368. Min Act: -0.1700
Data Index: 7218216 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1868. Min Range: -7.1868
Max Act: 6.4368. Min Act: -0.1700
Data Index: 1566904 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19