Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1125 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3796. Min Range: -3.3796
Max Act: 3.3796. Min Act: -0.1700
Data Index: 6040132 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3796. Min Range: -3.3796
Max Act: 3.2383. Min Act: -0.1700
Data Index: 4575026 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3796. Min Range: -3.3796
Max Act: 3.1125. Min Act: -0.1700
Data Index: 2338815 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3796. Min Range: -3.3796
Max Act: 3.0809. Min Act: -0.1700
Data Index: 2427248 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3796. Min Range: -3.3796
Max Act: 3.0967. Min Act: -0.1700
Data Index: 6040133 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3796. Min Range: -3.3796
Max Act: 3.0494. Min Act: -0.1700
Data Index: 6588632 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3796. Min Range: -3.3796
Max Act: 3.0967. Min Act: -0.1700
Data Index: 2107302 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3796. Min Range: -3.3796
Max Act: 3.0494. Min Act: -0.1700
Data Index: 4459432 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3796. Min Range: -3.3796
Max Act: 3.0652. Min Act: -0.1700
Data Index: 5122108 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3796. Min Range: -3.3796
Max Act: 3.0178. Min Act: -0.1700
Data Index: 4728582 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3796. Min Range: -3.3796
Max Act: 3.0336. Min Act: -0.1700
Data Index: 5273458 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3796. Min Range: -3.3796
Max Act: 3.0494. Min Act: -0.1700
Data Index: 5036996 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3796. Min Range: -3.3796
Max Act: 3.0020. Min Act: -0.1700
Data Index: 4327557 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3796. Min Range: -3.3796
Max Act: 2.9862. Min Act: -0.1700
Data Index: 4122791 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3796. Min Range: -3.3796
Max Act: 2.9862. Min Act: -0.1700
Data Index: 4540795 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3796. Min Range: -3.3796
Max Act: 2.9704. Min Act: -0.1700
Data Index: 48160 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3796. Min Range: -3.3796
Max Act: 2.9546. Min Act: -0.1700
Data Index: 5312572 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3796. Min Range: -3.3796
Max Act: 2.9704. Min Act: -0.1700
Data Index: 1167617 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3796. Min Range: -3.3796
Max Act: 2.9704. Min Act: -0.1700
Data Index: 6762542 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3796. Min Range: -3.3796
Max Act: 2.9387. Min Act: -0.1700
Data Index: 1813464 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19