Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1971 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2107. Min Range: -7.2107
Max Act: 7.2107. Min Act: -0.1700
Data Index: 2490745 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2107. Min Range: -7.2107
Max Act: 7.1170. Min Act: -0.1700
Data Index: 4179647 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2107. Min Range: -7.2107
Max Act: 7.0857. Min Act: -0.1700
Data Index: 8099672 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2107. Min Range: -7.2107
Max Act: 7.0545. Min Act: -0.1700
Data Index: 6172873 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.7732. Min Act: -0.1700
Data Index: 1443223 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.7420. Min Act: -0.1700
Data Index: 4387580 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.7732. Min Act: -0.1700
Data Index: 676959 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.7420. Min Act: -0.1700
Data Index: 3362305 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.6795. Min Act: -0.1700
Data Index: 1753654 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.6795. Min Act: -0.1700
Data Index: 4999489 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.7107. Min Act: -0.1700
Data Index: 7679857 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.6795. Min Act: -0.1700
Data Index: 7553346 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.6482. Min Act: -0.1700
Data Index: 6220096 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.6482. Min Act: -0.1700
Data Index: 5819849 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.6482. Min Act: -0.1700
Data Index: 7450132 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.6170. Min Act: -0.1700
Data Index: 5238731 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.6795. Min Act: -0.1700
Data Index: 2378316 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.5232. Min Act: -0.1700
Data Index: 7553333 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.5232. Min Act: -0.1700
Data Index: 3653810 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2107. Min Range: -7.2107
Max Act: 6.5545. Min Act: -0.1700
Data Index: 7404713 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19