Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 238 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.4572. Min Act: -0.1700
Data Index: 8752934 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.3635. Min Act: -0.1700
Data Index: 4838537 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.3322. Min Act: -0.1700
Data Index: 4559339 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.2697. Min Act: -0.1700
Data Index: 1901418 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.2072. Min Act: -0.1700
Data Index: 43917 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.2072. Min Act: -0.1700
Data Index: 6959444 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.1760. Min Act: -0.1700
Data Index: 7324205 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.2072. Min Act: -0.1700
Data Index: 8304451 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.1135. Min Act: -0.1700
Data Index: 1409364 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.1135. Min Act: -0.1700
Data Index: 5208999 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.1135. Min Act: -0.1700
Data Index: 768495 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.0822. Min Act: -0.1700
Data Index: 4855640 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.0822. Min Act: -0.1700
Data Index: 116923 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.0197. Min Act: -0.1700
Data Index: 8636896 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.0510. Min Act: -0.1700
Data Index: 3169890 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.0197. Min Act: -0.1700
Data Index: 1660234 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.0510. Min Act: -0.1700
Data Index: 5248648 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.0510. Min Act: -0.1700
Data Index: 3847291 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.0197. Min Act: -0.1700
Data Index: 1120255 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4572. Min Range: -5.4572
Max Act: 5.0510. Min Act: -0.1700
Data Index: 511700 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19