Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2101 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.9930. Min Act: -0.1700
Data Index: 3950944 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.5243. Min Act: -0.1700
Data Index: 2907057 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.3993. Min Act: -0.1700
Data Index: 40273 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.3368. Min Act: -0.1700
Data Index: 417964 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.2430. Min Act: -0.1700
Data Index: 3761214 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.2118. Min Act: -0.1700
Data Index: 512780 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.1493. Min Act: -0.1700
Data Index: 7646607 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.1493. Min Act: -0.1700
Data Index: 4684469 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.1493. Min Act: -0.1700
Data Index: 6147802 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.0868. Min Act: -0.1700
Data Index: 6079344 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.0868. Min Act: -0.1700
Data Index: 8478471 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.0868. Min Act: -0.1700
Data Index: 8478461 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.0868. Min Act: -0.1700
Data Index: 3982743 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.0555. Min Act: -0.1700
Data Index: 8478452 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9930. Min Range: -7.9930
Max Act: 7.0243. Min Act: -0.1700
Data Index: 2859301 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9930. Min Range: -7.9930
Max Act: 6.9930. Min Act: -0.1700
Data Index: 6145414 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9930. Min Range: -7.9930
Max Act: 6.9305. Min Act: -0.1700
Data Index: 3184788 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9930. Min Range: -7.9930
Max Act: 6.9618. Min Act: -0.1700
Data Index: 81005 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9930. Min Range: -7.9930
Max Act: 6.9618. Min Act: -0.1700
Data Index: 4763132 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9930. Min Range: -7.9930
Max Act: 6.9618. Min Act: -0.1700
Data Index: 2880800 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19