Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2434 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0992. Min Range: -5.0992
Max Act: 5.0992. Min Act: -0.1700
Data Index: 3917091 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0992. Min Range: -5.0992
Max Act: 5.0367. Min Act: -0.1700
Data Index: 2793265 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0992. Min Range: -5.0992
Max Act: 5.0367. Min Act: -0.1700
Data Index: 6762847 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0992. Min Range: -5.0992
Max Act: 5.0367. Min Act: -0.1700
Data Index: 1194059 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0992. Min Range: -5.0992
Max Act: 5.0054. Min Act: -0.1700
Data Index: 482034 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0992. Min Range: -5.0992
Max Act: 5.0054. Min Act: -0.1700
Data Index: 2551591 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0992. Min Range: -5.0992
Max Act: 4.9742. Min Act: -0.1700
Data Index: 928344 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0992. Min Range: -5.0992
Max Act: 4.9742. Min Act: -0.1700
Data Index: 3386731 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0992. Min Range: -5.0992
Max Act: 4.9742. Min Act: -0.1700
Data Index: 107764 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0992. Min Range: -5.0992
Max Act: 4.9742. Min Act: -0.1700
Data Index: 3943964 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0992. Min Range: -5.0992
Max Act: 4.9429. Min Act: -0.1700
Data Index: 7514600 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0992. Min Range: -5.0992
Max Act: 4.9117. Min Act: -0.1700
Data Index: 2559684 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0992. Min Range: -5.0992
Max Act: 4.9117. Min Act: -0.1700
Data Index: 6281767 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0992. Min Range: -5.0992
Max Act: 4.9117. Min Act: -0.1700
Data Index: 2933952 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0992. Min Range: -5.0992
Max Act: 4.9117. Min Act: -0.1700
Data Index: 3536702 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0992. Min Range: -5.0992
Max Act: 4.8804. Min Act: -0.1700
Data Index: 6166304 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0992. Min Range: -5.0992
Max Act: 4.8804. Min Act: -0.1700
Data Index: 5484687 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0992. Min Range: -5.0992
Max Act: 4.8804. Min Act: -0.1700
Data Index: 3036089 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0992. Min Range: -5.0992
Max Act: 4.8179. Min Act: -0.1700
Data Index: 2995828 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0992. Min Range: -5.0992
Max Act: 4.8492. Min Act: -0.1700
Data Index: 3524126 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19