Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2500 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3628. Min Range: -3.3628
Max Act: 3.3628. Min Act: -0.1700
Data Index: 3853426 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3628. Min Range: -3.3628
Max Act: 3.3000. Min Act: -0.1700
Data Index: 438246 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3628. Min Range: -3.3628
Max Act: 3.2215. Min Act: -0.1700
Data Index: 1162120 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3628. Min Range: -3.3628
Max Act: 3.1900. Min Act: -0.1700
Data Index: 4362627 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3628. Min Range: -3.3628
Max Act: 3.1900. Min Act: -0.1700
Data Index: 7994824 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3628. Min Range: -3.3628
Max Act: 3.1428. Min Act: -0.1700
Data Index: 8406434 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3628. Min Range: -3.3628
Max Act: 3.0956. Min Act: -0.1700
Data Index: 1084215 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3628. Min Range: -3.3628
Max Act: 3.0640. Min Act: -0.1700
Data Index: 3563067 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3628. Min Range: -3.3628
Max Act: 2.9693. Min Act: -0.1700
Data Index: 6426928 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3628. Min Range: -3.3628
Max Act: 2.9851. Min Act: -0.1700
Data Index: 5330485 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3628. Min Range: -3.3628
Max Act: 2.9693. Min Act: -0.1700
Data Index: 5524518 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3628. Min Range: -3.3628
Max Act: 2.9534. Min Act: -0.1700
Data Index: 6392363 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3628. Min Range: -3.3628
Max Act: 2.9376. Min Act: -0.1700
Data Index: 1648456 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3628. Min Range: -3.3628
Max Act: 2.9059. Min Act: -0.1700
Data Index: 6621308 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3628. Min Range: -3.3628
Max Act: 2.8900. Min Act: -0.1700
Data Index: 1842437 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3628. Min Range: -3.3628
Max Act: 2.8742. Min Act: -0.1700
Data Index: 7561332 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3628. Min Range: -3.3628
Max Act: 2.8424. Min Act: -0.1700
Data Index: 5305985 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3628. Min Range: -3.3628
Max Act: 2.8900. Min Act: -0.1700
Data Index: 1201503 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3628. Min Range: -3.3628
Max Act: 2.8742. Min Act: -0.1700
Data Index: 3915310 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3628. Min Range: -3.3628
Max Act: 2.7468. Min Act: -0.1700
Data Index: 384811 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19