Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2909 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2202. Min Range: -4.2202
Max Act: 4.2202. Min Act: -0.1700
Data Index: 7807391 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2202. Min Range: -4.2202
Max Act: 4.0327. Min Act: -0.1700
Data Index: 8490572 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.9701. Min Act: -0.1700
Data Index: 6323894 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.9701. Min Act: -0.1700
Data Index: 1545571 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.9701. Min Act: -0.1700
Data Index: 4496096 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.9076. Min Act: -0.1700
Data Index: 130266 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.9076. Min Act: -0.1700
Data Index: 8270455 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.8607. Min Act: -0.1700
Data Index: 6785157 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.8607. Min Act: -0.1700
Data Index: 4080261 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.8295. Min Act: -0.1700
Data Index: 7694262 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.8607. Min Act: -0.1700
Data Index: 130273 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.8138. Min Act: -0.1700
Data Index: 6867549 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.8138. Min Act: -0.1700
Data Index: 5909687 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.8295. Min Act: -0.1700
Data Index: 2034605 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.8451. Min Act: -0.1700
Data Index: 1545573 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.7982. Min Act: -0.1700
Data Index: 5891967 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.8138. Min Act: -0.1700
Data Index: 8110553 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.8138. Min Act: -0.1700
Data Index: 1995292 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.8138. Min Act: -0.1700
Data Index: 6175450 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2202. Min Range: -4.2202
Max Act: 3.7982. Min Act: -0.1700
Data Index: 5652023 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19