Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.2280. Min Act: -0.1700
Data Index: 954755 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.2016. Min Act: -0.1700
Data Index: 2924528 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1840. Min Act: -0.1700
Data Index: 4894880 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1664. Min Act: -0.1700
Data Index: 5964769 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1576. Min Act: -0.1700
Data Index: 164073 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1576. Min Act: -0.1700
Data Index: 3153074 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1576. Min Act: -0.1700
Data Index: 8611169 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1576. Min Act: -0.1700
Data Index: 3031369 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1576. Min Act: -0.1700
Data Index: 5354536 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1576. Min Act: -0.1700
Data Index: 5472265 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1488. Min Act: -0.1700
Data Index: 8622691 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1488. Min Act: -0.1694
Data Index: 748877 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1576. Min Act: -0.1700
Data Index: 1417023 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1400. Min Act: -0.1699
Data Index: 246920 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1312. Min Act: -0.1700
Data Index: 5957798 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1400. Min Act: -0.1700
Data Index: 5582470 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1312. Min Act: -0.1700
Data Index: 3195330 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1400. Min Act: -0.1700
Data Index: 4399499 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1400. Min Act: -0.1700
Data Index: 1708389 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2280. Min Range: -1.2280
Max Act: 1.1400. Min Act: -0.1700
Data Index: 2025331 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19