Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3869 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0869. Min Range: -5.0869
Max Act: 5.0869. Min Act: -0.1700
Data Index: 279251 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0869. Min Range: -5.0869
Max Act: 5.0557. Min Act: -0.1700
Data Index: 7386286 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0869. Min Range: -5.0869
Max Act: 5.0244. Min Act: -0.1700
Data Index: 7822263 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.9932. Min Act: -0.1700
Data Index: 2202248 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.9932. Min Act: -0.1700
Data Index: 3814974 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.9619. Min Act: -0.1700
Data Index: 7263161 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.8994. Min Act: -0.1700
Data Index: 3039432 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.8682. Min Act: -0.1700
Data Index: 3815520 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.8994. Min Act: -0.1700
Data Index: 8054341 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.8682. Min Act: -0.1700
Data Index: 6225395 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.8994. Min Act: -0.1700
Data Index: 533953 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.8682. Min Act: -0.1700
Data Index: 5214178 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.8369. Min Act: -0.1700
Data Index: 4902201 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.8682. Min Act: -0.1700
Data Index: 36971 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.8369. Min Act: -0.1700
Data Index: 233054 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.8369. Min Act: -0.1700
Data Index: 8602016 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.8369. Min Act: -0.1700
Data Index: 7898835 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.8369. Min Act: -0.1700
Data Index: 533954 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.8369. Min Act: -0.1700
Data Index: 4000285 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0869. Min Range: -5.0869
Max Act: 4.8057. Min Act: -0.1700
Data Index: 5983533 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19