Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.6239. Min Act: -0.1700
Data Index: 6710489 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.5927. Min Act: -0.1700
Data Index: 5925139 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.3427. Min Act: -0.1700
Data Index: 7074429 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.3427. Min Act: -0.1700
Data Index: 1335535 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.3427. Min Act: -0.1700
Data Index: 1335546 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.2489. Min Act: -0.1700
Data Index: 5593477 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.2177. Min Act: -0.1700
Data Index: 234788 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.1864. Min Act: -0.1700
Data Index: 53946 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.1552. Min Act: -0.1700
Data Index: 7774503 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.1552. Min Act: -0.1700
Data Index: 4304520 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.1239. Min Act: -0.1700
Data Index: 2304418 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.0927. Min Act: -0.1700
Data Index: 4027871 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.1239. Min Act: -0.1700
Data Index: 4575059 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.1239. Min Act: -0.1700
Data Index: 6953695 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.0927. Min Act: -0.1700
Data Index: 2437321 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.1239. Min Act: -0.1700
Data Index: 2721801 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.0927. Min Act: -0.1700
Data Index: 8379283 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.0614. Min Act: -0.1700
Data Index: 5892091 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.0614. Min Act: -0.1700
Data Index: 5920591 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6239. Min Range: -5.6239
Max Act: 5.0302. Min Act: -0.1700
Data Index: 8276946 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19