Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.6187. Min Act: -0.1700
Data Index: 945310 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.5874. Min Act: -0.1700
Data Index: 2275477 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.5874. Min Act: -0.1700
Data Index: 6783770 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.5874. Min Act: -0.1700
Data Index: 3844788 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.5561. Min Act: -0.1700
Data Index: 7204726 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.5092. Min Act: -0.1700
Data Index: 8322839 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.4935. Min Act: -0.1700
Data Index: 1456253 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.4778. Min Act: -0.1700
Data Index: 3084361 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.4778. Min Act: -0.1700
Data Index: 226965 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.4935. Min Act: -0.1700
Data Index: 7684246 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.4622. Min Act: -0.1700
Data Index: 2770409 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.4465. Min Act: -0.1700
Data Index: 226963 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.4465. Min Act: -0.1700
Data Index: 3090552 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.4308. Min Act: -0.1700
Data Index: 3395351 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.4308. Min Act: -0.1700
Data Index: 2669265 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.4308. Min Act: -0.1700
Data Index: 6613460 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.4308. Min Act: -0.1700
Data Index: 6108654 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.4151. Min Act: -0.1700
Data Index: 1837366 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.4151. Min Act: -0.1700
Data Index: 6639476 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6187. Min Range: -3.6187
Max Act: 3.4308. Min Act: -0.1700
Data Index: 2094111 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19