Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 890 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1978. Min Range: -7.1978
Max Act: 7.1978. Min Act: -0.1700
Data Index: 4982178 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1978. Min Range: -7.1978
Max Act: 7.0103. Min Act: -0.1700
Data Index: 6628381 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1978. Min Range: -7.1978
Max Act: 7.0103. Min Act: -0.1700
Data Index: 5335156 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.9790. Min Act: -0.1700
Data Index: 2942131 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.7603. Min Act: -0.1700
Data Index: 6272936 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.7603. Min Act: -0.1700
Data Index: 3134502 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.6978. Min Act: -0.1700
Data Index: 7320046 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.5415. Min Act: -0.1700
Data Index: 7392017 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.4790. Min Act: -0.1700
Data Index: 4979196 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.5103. Min Act: -0.1700
Data Index: 3253420 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.5103. Min Act: -0.1700
Data Index: 1088578 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.5103. Min Act: -0.1700
Data Index: 8287240 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.4790. Min Act: -0.1700
Data Index: 3506277 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.4790. Min Act: -0.1700
Data Index: 781335 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.4478. Min Act: -0.1700
Data Index: 131279 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.4790. Min Act: -0.1700
Data Index: 4330504 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.4478. Min Act: -0.1700
Data Index: 8173050 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.4165. Min Act: -0.1700
Data Index: 8111118 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.4165. Min Act: -0.1700
Data Index: 4641948 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.4165. Min Act: -0.1700
Data Index: 5045925 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19