Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.3244. Min Act: -0.1700
Data Index: 5455434 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.2307. Min Act: -0.1700
Data Index: 3554970 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.2619. Min Act: -0.1700
Data Index: 7689450 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1994. Min Act: -0.1700
Data Index: 4279366 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1994. Min Act: -0.1700
Data Index: 7513028 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1682. Min Act: -0.1700
Data Index: 3477846 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1994. Min Act: -0.1700
Data Index: 5305120 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1682. Min Act: -0.1700
Data Index: 1390224 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1682. Min Act: -0.1700
Data Index: 8496149 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1369. Min Act: -0.1700
Data Index: 4101378 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1682. Min Act: -0.1700
Data Index: 8537882 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1369. Min Act: -0.1699
Data Index: 6813742 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1369. Min Act: -0.1700
Data Index: 5734752 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1682. Min Act: -0.1700
Data Index: 4458491 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1682. Min Act: -0.1700
Data Index: 3354035 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1682. Min Act: -0.1700
Data Index: 1186903 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1369. Min Act: -0.1700
Data Index: 3044475 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1057. Min Act: -0.1700
Data Index: 474912 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1369. Min Act: -0.1700
Data Index: 4144724 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3244. Min Range: -5.3244
Max Act: 5.1682. Min Act: -0.1700
Data Index: 5094773 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19