Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3755 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.4162. Min Act: -0.1700
Data Index: 1576166 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.3848. Min Act: -0.1700
Data Index: 513492 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.3692. Min Act: -0.1700
Data Index: 4226634 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.3221. Min Act: -0.1700
Data Index: 3371309 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2907. Min Act: -0.1700
Data Index: 1756530 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.3064. Min Act: -0.1700
Data Index: 8557601 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2907. Min Act: -0.1700
Data Index: 7125545 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2907. Min Act: -0.1700
Data Index: 2053743 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2750. Min Act: -0.1700
Data Index: 1850691 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2750. Min Act: -0.1700
Data Index: 3308502 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2750. Min Act: -0.1700
Data Index: 1484464 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2750. Min Act: -0.1700
Data Index: 4389604 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2436. Min Act: -0.1700
Data Index: 30684 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2593. Min Act: -0.1700
Data Index: 710994 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2750. Min Act: -0.1700
Data Index: 2101589 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2279. Min Act: -0.1700
Data Index: 1665259 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2279. Min Act: -0.1700
Data Index: 2291869 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2279. Min Act: -0.1700
Data Index: 2546027 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2436. Min Act: -0.1700
Data Index: 6642880 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4162. Min Range: -3.4162
Max Act: 3.2279. Min Act: -0.1700
Data Index: 2712314 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19