Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0657. Min Range: -2.0657
Max Act: 2.0657. Min Act: -0.1700
Data Index: 5699437 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0657. Min Range: -2.0657
Max Act: 2.0152. Min Act: -0.1700
Data Index: 2188561 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9983. Min Act: -0.1700
Data Index: 1354577 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9983. Min Act: -0.1700
Data Index: 5515905 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9983. Min Act: -0.1700
Data Index: 2948469 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9814. Min Act: -0.1700
Data Index: 1831730 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9645. Min Act: -0.1699
Data Index: 7864223 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9475. Min Act: -0.1700
Data Index: 4005195 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9475. Min Act: -0.1700
Data Index: 5360272 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9475. Min Act: -0.1700
Data Index: 1622461 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9645. Min Act: -0.1700
Data Index: 6983787 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9475. Min Act: -0.1700
Data Index: 4558778 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9475. Min Act: -0.1700
Data Index: 4140948 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9475. Min Act: -0.1700
Data Index: 130345 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9305. Min Act: -0.1700
Data Index: 5340506 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9135. Min Act: -0.1700
Data Index: 2810034 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9305. Min Act: -0.1700
Data Index: 3587423 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9305. Min Act: -0.1700
Data Index: 5437582 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9305. Min Act: -0.1700
Data Index: 737166 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0657. Min Range: -2.0657
Max Act: 1.9305. Min Act: -0.1700
Data Index: 3672592 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19