Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2315 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1493. Min Range: -3.1493
Max Act: 3.1493. Min Act: -0.1700
Data Index: 7624606 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.9125. Min Act: -0.1700
Data Index: 4284444 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.9125. Min Act: -0.1700
Data Index: 3848838 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.8966. Min Act: -0.1700
Data Index: 1454555 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.8807. Min Act: -0.1700
Data Index: 1071143 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.8649. Min Act: -0.1700
Data Index: 6646273 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.8807. Min Act: -0.1700
Data Index: 7624593 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.8490. Min Act: -0.1700
Data Index: 7946391 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.8807. Min Act: -0.1700
Data Index: 4794707 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.8331. Min Act: -0.1700
Data Index: 8415001 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.8490. Min Act: -0.1700
Data Index: 4407579 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.8490. Min Act: -0.1700
Data Index: 7522587 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.8331. Min Act: -0.1700
Data Index: 332996 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.8490. Min Act: -0.1700
Data Index: 3706565 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.7853. Min Act: -0.1700
Data Index: 5066787 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.7694. Min Act: -0.1700
Data Index: 882308 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.7853. Min Act: -0.1700
Data Index: 2717240 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.7534. Min Act: -0.1700
Data Index: 1959938 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.7534. Min Act: -0.1700
Data Index: 1071139 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1493. Min Range: -3.1493
Max Act: 2.7694. Min Act: -0.1700
Data Index: 7022499 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19