Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4046 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.5154. Min Act: -0.1700
Data Index: 376121 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.4058. Min Act: -0.1700
Data Index: 8432689 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3901. Min Act: -0.1700
Data Index: 5667939 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3744. Min Act: -0.1700
Data Index: 1067367 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3587. Min Act: -0.1700
Data Index: 5533262 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3744. Min Act: -0.1700
Data Index: 8040400 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3744. Min Act: -0.1700
Data Index: 4469274 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3430. Min Act: -0.1700
Data Index: 4371919 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3587. Min Act: -0.1700
Data Index: 58428 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3587. Min Act: -0.1700
Data Index: 8604186 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3430. Min Act: -0.1700
Data Index: 5588122 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3430. Min Act: -0.1700
Data Index: 7372536 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3430. Min Act: -0.1700
Data Index: 4838983 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3273. Min Act: -0.1700
Data Index: 3858267 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3587. Min Act: -0.1700
Data Index: 6104335 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3116. Min Act: -0.1700
Data Index: 610505 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3273. Min Act: -0.1700
Data Index: 8278293 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.2959. Min Act: -0.1700
Data Index: 8172204 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.3116. Min Act: -0.1700
Data Index: 3858265 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5154. Min Range: -3.5154
Max Act: 3.2959. Min Act: -0.1700
Data Index: 3064756 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19