Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5316 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0759. Min Range: -7.0759
Max Act: 7.0759. Min Act: -0.1700
Data Index: 2378586 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.9822. Min Act: -0.1700
Data Index: 8806616 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.9197. Min Act: -0.1700
Data Index: 6927293 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.9197. Min Act: -0.1700
Data Index: 5391691 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.8884. Min Act: -0.1700
Data Index: 4471059 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.8884. Min Act: -0.1700
Data Index: 4714293 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.8259. Min Act: -0.1700
Data Index: 36231 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.7947. Min Act: -0.1700
Data Index: 4511047 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.7947. Min Act: -0.1700
Data Index: 2984770 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.7947. Min Act: -0.1700
Data Index: 1970116 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.7634. Min Act: -0.1700
Data Index: 8442339 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.7634. Min Act: -0.1700
Data Index: 2143667 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.7009. Min Act: -0.1700
Data Index: 3271110 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.7009. Min Act: -0.1700
Data Index: 360308 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.7009. Min Act: -0.1700
Data Index: 623905 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.6384. Min Act: -0.1700
Data Index: 4433032 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.6384. Min Act: -0.1700
Data Index: 1677517 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.6384. Min Act: -0.1700
Data Index: 5039291 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.6384. Min Act: -0.1700
Data Index: 2000825 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0759. Min Range: -7.0759
Max Act: 6.6072. Min Act: -0.1700
Data Index: 4743803 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19