Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2033 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4224. Min Range: -6.4224
Max Act: 6.4224. Min Act: -0.1700
Data Index: 5795301 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4224. Min Range: -6.4224
Max Act: 6.4224. Min Act: -0.1700
Data Index: 267193 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4224. Min Range: -6.4224
Max Act: 6.3911. Min Act: -0.1700
Data Index: 1889816 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4224. Min Range: -6.4224
Max Act: 6.3286. Min Act: -0.1700
Data Index: 2197141 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4224. Min Range: -6.4224
Max Act: 6.1724. Min Act: -0.1700
Data Index: 8236155 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4224. Min Range: -6.4224
Max Act: 6.1411. Min Act: -0.1700
Data Index: 2798437 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4224. Min Range: -6.4224
Max Act: 6.0786. Min Act: -0.1700
Data Index: 669763 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4224. Min Range: -6.4224
Max Act: 6.1099. Min Act: -0.1700
Data Index: 1875495 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4224. Min Range: -6.4224
Max Act: 6.0786. Min Act: -0.1700
Data Index: 1277864 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4224. Min Range: -6.4224
Max Act: 6.0786. Min Act: -0.1700
Data Index: 6370268 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4224. Min Range: -6.4224
Max Act: 6.0474. Min Act: -0.1700
Data Index: 7197374 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4224. Min Range: -6.4224
Max Act: 6.0161. Min Act: -0.1700
Data Index: 4468783 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4224. Min Range: -6.4224
Max Act: 6.0161. Min Act: -0.1700
Data Index: 2681564 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4224. Min Range: -6.4224
Max Act: 5.9849. Min Act: -0.1700
Data Index: 1480275 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4224. Min Range: -6.4224
Max Act: 6.0161. Min Act: -0.1700
Data Index: 1520862 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4224. Min Range: -6.4224
Max Act: 5.9849. Min Act: -0.1700
Data Index: 3344361 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4224. Min Range: -6.4224
Max Act: 5.9536. Min Act: -0.1700
Data Index: 2681596 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4224. Min Range: -6.4224
Max Act: 5.9224. Min Act: -0.1700
Data Index: 4192282 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4224. Min Range: -6.4224
Max Act: 5.9224. Min Act: -0.1700
Data Index: 1653968 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4224. Min Range: -6.4224
Max Act: 5.9536. Min Act: -0.1700
Data Index: 81353 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19