Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2753 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.3229. Min Act: -0.1700
Data Index: 6546400 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.3229. Min Act: -0.1700
Data Index: 3954252 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.3229. Min Act: -0.1700
Data Index: 5402664 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2735. Min Act: -0.1700
Data Index: 3777969 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2900. Min Act: -0.1700
Data Index: 5563407 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2900. Min Act: -0.1700
Data Index: 3321711 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2900. Min Act: -0.1700
Data Index: 7449709 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2900. Min Act: -0.1700
Data Index: 2410923 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2570. Min Act: -0.1700
Data Index: 60128 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2570. Min Act: -0.1700
Data Index: 6680239 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2570. Min Act: -0.1700
Data Index: 2758605 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2570. Min Act: -0.1700
Data Index: 6090184 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2405. Min Act: -0.1700
Data Index: 6480833 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2570. Min Act: -0.1700
Data Index: 3519357 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2570. Min Act: -0.1700
Data Index: 6680096 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2570. Min Act: -0.1700
Data Index: 5899491 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2405. Min Act: -0.1700
Data Index: 3405622 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2405. Min Act: -0.1700
Data Index: 220807 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2405. Min Act: -0.1700
Data Index: 2246268 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3229. Min Range: -2.3229
Max Act: 2.2570. Min Act: -0.1700
Data Index: 3737363 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19