Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0033. Min Range: -5.0033
Max Act: 5.0033. Min Act: -0.1700
Data Index: 7026856 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0033. Min Range: -5.0033
Max Act: 5.0033. Min Act: -0.1700
Data Index: 6163521 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.9095. Min Act: -0.1700
Data Index: 896685 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.8470. Min Act: -0.1700
Data Index: 3120271 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.8158. Min Act: -0.1700
Data Index: 1064140 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.8158. Min Act: -0.1700
Data Index: 4367128 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.8158. Min Act: -0.1700
Data Index: 4581196 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.7533. Min Act: -0.1700
Data Index: 2895256 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.7845. Min Act: -0.1700
Data Index: 2641350 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.7533. Min Act: -0.1700
Data Index: 4869368 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.7533. Min Act: -0.1700
Data Index: 4929907 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.7220. Min Act: -0.1700
Data Index: 3134042 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.7220. Min Act: -0.1700
Data Index: 5186432 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.7220. Min Act: -0.1700
Data Index: 6823954 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.7220. Min Act: -0.1700
Data Index: 8798347 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.7220. Min Act: -0.1700
Data Index: 4327364 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.6908. Min Act: -0.1700
Data Index: 4407358 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.6908. Min Act: -0.1700
Data Index: 2282492 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.6595. Min Act: -0.1700
Data Index: 7793868 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0033. Min Range: -5.0033
Max Act: 4.6908. Min Act: -0.1700
Data Index: 8672783 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19