Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2868 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0280. Min Range: -8.0280
Max Act: 8.0280. Min Act: -0.1700
Data Index: 6302870 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.9342. Min Act: -0.1700
Data Index: 1578024 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.9030. Min Act: -0.1700
Data Index: 238535 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.6530. Min Act: -0.1700
Data Index: 7558864 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.6530. Min Act: -0.1700
Data Index: 464122 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.5280. Min Act: -0.1700
Data Index: 2397281 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.4655. Min Act: -0.1700
Data Index: 3970186 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.4967. Min Act: -0.1700
Data Index: 4328702 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.5280. Min Act: -0.1700
Data Index: 7100057 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.4655. Min Act: -0.1700
Data Index: 7612197 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.5592. Min Act: -0.1700
Data Index: 7304817 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.4342. Min Act: -0.1700
Data Index: 8069466 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.4967. Min Act: -0.1700
Data Index: 3001708 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.5280. Min Act: -0.1700
Data Index: 4051039 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.4342. Min Act: -0.1700
Data Index: 359906 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.4342. Min Act: -0.1700
Data Index: 8005811 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.4030. Min Act: -0.1700
Data Index: 6548471 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.4342. Min Act: -0.1700
Data Index: 8504261 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.4342. Min Act: -0.1700
Data Index: 4779227 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0280. Min Range: -8.0280
Max Act: 7.2780. Min Act: -0.1700
Data Index: 6411659 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19