Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3035 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2323. Min Range: -7.2323
Max Act: 7.2323. Min Act: -0.1700
Data Index: 5592526 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2323. Min Range: -7.2323
Max Act: 7.1698. Min Act: -0.1700
Data Index: 3177634 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2323. Min Range: -7.2323
Max Act: 7.0448. Min Act: -0.1700
Data Index: 969970 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.9198. Min Act: -0.1700
Data Index: 3732496 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.9198. Min Act: -0.1700
Data Index: 4502576 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.9198. Min Act: -0.1700
Data Index: 8449748 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.8573. Min Act: -0.1700
Data Index: 6985795 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.8573. Min Act: -0.1700
Data Index: 8449745 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.8573. Min Act: -0.1700
Data Index: 2749520 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.8573. Min Act: -0.1700
Data Index: 8154566 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.7948. Min Act: -0.1700
Data Index: 4810017 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.7948. Min Act: -0.1700
Data Index: 6806711 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.7948. Min Act: -0.1700
Data Index: 136238 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.7948. Min Act: -0.1700
Data Index: 6376901 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.7948. Min Act: -0.1700
Data Index: 6498841 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.7948. Min Act: -0.1700
Data Index: 6781610 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.7323. Min Act: -0.1700
Data Index: 962390 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.7323. Min Act: -0.1700
Data Index: 669665 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.7323. Min Act: -0.1700
Data Index: 5015121 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2323. Min Range: -7.2323
Max Act: 6.7323. Min Act: -0.1700
Data Index: 349453 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19