Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 306 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.3614. Min Act: -0.1700
Data Index: 3160119 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.3614. Min Act: -0.1700
Data Index: 8395942 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.3301. Min Act: -0.1700
Data Index: 4609324 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.2676. Min Act: -0.1700
Data Index: 4959119 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.2364. Min Act: -0.1700
Data Index: 6881243 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.2364. Min Act: -0.1700
Data Index: 4178316 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.2364. Min Act: -0.1700
Data Index: 295430 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.2051. Min Act: -0.1700
Data Index: 7275341 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.2051. Min Act: -0.1700
Data Index: 7474785 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.2051. Min Act: -0.1700
Data Index: 5853036 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.1426. Min Act: -0.1700
Data Index: 8111332 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.1739. Min Act: -0.1700
Data Index: 1750329 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.1426. Min Act: -0.1700
Data Index: 2223762 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.1426. Min Act: -0.1700
Data Index: 7654355 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.1739. Min Act: -0.1700
Data Index: 789676 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.1426. Min Act: -0.1700
Data Index: 1175178 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.1426. Min Act: -0.1700
Data Index: 7092258 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.1739. Min Act: -0.1700
Data Index: 1939631 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.1426. Min Act: -0.1700
Data Index: 1025673 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3614. Min Range: -5.3614
Max Act: 5.1426. Min Act: -0.1700
Data Index: 1103643 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19