Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3704 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.7135. Min Act: -0.1700
Data Index: 4195250 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6975. Min Act: -0.1700
Data Index: 6658229 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6815. Min Act: -0.1700
Data Index: 2669528 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6655. Min Act: -0.1700
Data Index: 3462397 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6655. Min Act: -0.1700
Data Index: 8246466 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6655. Min Act: -0.1700
Data Index: 1472608 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6494. Min Act: -0.1700
Data Index: 7416027 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6334. Min Act: -0.1700
Data Index: 4580722 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6173. Min Act: -0.1700
Data Index: 3047523 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6334. Min Act: -0.1700
Data Index: 1226606 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6334. Min Act: -0.1700
Data Index: 2974307 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6334. Min Act: -0.1700
Data Index: 7383884 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6334. Min Act: -0.1700
Data Index: 7206578 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6334. Min Act: -0.1700
Data Index: 1224824 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6334. Min Act: -0.1700
Data Index: 6995853 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6334. Min Act: -0.1700
Data Index: 275298 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6334. Min Act: -0.1700
Data Index: 3295796 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6173. Min Act: -0.1700
Data Index: 2678985 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6012. Min Act: -0.1700
Data Index: 3186570 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7135. Min Range: -2.7135
Max Act: 2.6173. Min Act: -0.1700
Data Index: 7391105 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19