Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1616 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.5016. Min Act: -0.1700
Data Index: 3403651 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.4703. Min Act: -0.1700
Data Index: 4245229 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.4233. Min Act: -0.1700
Data Index: 6698121 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.4389. Min Act: -0.1700
Data Index: 305156 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.4076. Min Act: -0.1700
Data Index: 1207275 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.3762. Min Act: -0.1700
Data Index: 5326918 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.3762. Min Act: -0.1700
Data Index: 3889986 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.3605. Min Act: -0.1700
Data Index: 4618305 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.3762. Min Act: -0.1700
Data Index: 3700245 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.3448. Min Act: -0.1700
Data Index: 6032886 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.3135. Min Act: -0.1700
Data Index: 5527677 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.2978. Min Act: -0.1700
Data Index: 6048468 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.2978. Min Act: -0.1700
Data Index: 83065 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.2821. Min Act: -0.1700
Data Index: 4503407 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.2664. Min Act: -0.1700
Data Index: 6388438 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.2664. Min Act: -0.1700
Data Index: 8803079 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.2664. Min Act: -0.1700
Data Index: 7203903 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.2349. Min Act: -0.1700
Data Index: 4642834 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.2349. Min Act: -0.1700
Data Index: 6048470 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5016. Min Range: -3.5016
Max Act: 3.2035. Min Act: -0.1700
Data Index: 4843643 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19