Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2525 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.3066. Min Act: -0.1700
Data Index: 3529193 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.2736. Min Act: -0.1700
Data Index: 6270572 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.2571. Min Act: -0.1700
Data Index: 5319895 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.2571. Min Act: -0.1700
Data Index: 6381972 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.2571. Min Act: -0.1700
Data Index: 6781530 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.2406. Min Act: -0.1700
Data Index: 3660177 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.2075. Min Act: -0.1700
Data Index: 2357118 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.2075. Min Act: -0.1700
Data Index: 6025452 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.2075. Min Act: -0.1700
Data Index: 4094027 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.2075. Min Act: -0.1700
Data Index: 194521 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1909. Min Act: -0.1700
Data Index: 5543165 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1909. Min Act: -0.1700
Data Index: 7886075 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1909. Min Act: -0.1700
Data Index: 4519367 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1743. Min Act: -0.1700
Data Index: 3153823 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1743. Min Act: -0.1700
Data Index: 8201250 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1743. Min Act: -0.1700
Data Index: 2399016 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1743. Min Act: -0.1700
Data Index: 5360612 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1743. Min Act: -0.1700
Data Index: 8282166 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1243. Min Act: -0.1700
Data Index: 5961892 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1243. Min Act: -0.1700
Data Index: 405975 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19