Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2001 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1881. Min Range: -5.1881
Max Act: 5.1881. Min Act: -0.1700
Data Index: 4338136 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1881. Min Range: -5.1881
Max Act: 5.0319. Min Act: -0.1700
Data Index: 2802890 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1881. Min Range: -5.1881
Max Act: 5.0006. Min Act: -0.1700
Data Index: 5244959 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.9694. Min Act: -0.1700
Data Index: 849613 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.9694. Min Act: -0.1700
Data Index: 2555735 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.9069. Min Act: -0.1700
Data Index: 3970815 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.9069. Min Act: -0.1700
Data Index: 4029080 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.9069. Min Act: -0.1700
Data Index: 2726109 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.9069. Min Act: -0.1700
Data Index: 6268389 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.9069. Min Act: -0.1700
Data Index: 2555736 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.8756. Min Act: -0.1700
Data Index: 6579249 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.8756. Min Act: -0.1700
Data Index: 6070629 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.8444. Min Act: -0.1700
Data Index: 4173309 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.8444. Min Act: -0.1700
Data Index: 4191260 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.8756. Min Act: -0.1700
Data Index: 249667 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.8444. Min Act: -0.1700
Data Index: 5579126 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.8131. Min Act: -0.1700
Data Index: 6625654 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.8131. Min Act: -0.1700
Data Index: 3973307 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.8131. Min Act: -0.1700
Data Index: 3602488 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1881. Min Range: -5.1881
Max Act: 4.7819. Min Act: -0.1700
Data Index: 6037877 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19