Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 535 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.8130. Min Act: -0.1700
Data Index: 8222827 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.7192. Min Act: -0.1700
Data Index: 6625279 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.7192. Min Act: -0.1700
Data Index: 422310 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.5942. Min Act: -0.1700
Data Index: 2407089 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.5942. Min Act: -0.1700
Data Index: 3082570 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.5630. Min Act: -0.1700
Data Index: 2010058 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.5317. Min Act: -0.1700
Data Index: 2010055 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.5317. Min Act: -0.1700
Data Index: 7140221 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.5317. Min Act: -0.1700
Data Index: 8222826 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.5317. Min Act: -0.1700
Data Index: 5734942 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.5317. Min Act: -0.1700
Data Index: 2407087 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.4692. Min Act: -0.1700
Data Index: 2407081 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.5005. Min Act: -0.1700
Data Index: 4036340 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.4692. Min Act: -0.1700
Data Index: 3082567 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.4380. Min Act: -0.1700
Data Index: 286559 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.4692. Min Act: -0.1700
Data Index: 8364430 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.4692. Min Act: -0.1700
Data Index: 1581942 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.4380. Min Act: -0.1700
Data Index: 6676141 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.4380. Min Act: -0.1700
Data Index: 2460765 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8130. Min Range: -4.8130
Max Act: 4.4067. Min Act: -0.1700
Data Index: 4036339 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19