Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3827 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.5594. Min Act: -0.1700
Data Index: 6200215 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.4969. Min Act: -0.1700
Data Index: 6938934 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.4969. Min Act: -0.1700
Data Index: 7158459 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.4344. Min Act: -0.1700
Data Index: 6669920 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.4656. Min Act: -0.1700
Data Index: 4747307 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.4031. Min Act: -0.1700
Data Index: 8787971 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.3719. Min Act: -0.1700
Data Index: 8474713 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.3719. Min Act: -0.1700
Data Index: 7108315 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.3406. Min Act: -0.1700
Data Index: 7809921 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.3094. Min Act: -0.1700
Data Index: 7010996 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.3406. Min Act: -0.1700
Data Index: 8444778 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.3406. Min Act: -0.1700
Data Index: 8441287 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.3094. Min Act: -0.1700
Data Index: 6235352 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.3094. Min Act: -0.1700
Data Index: 2970017 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.3094. Min Act: -0.1700
Data Index: 7556038 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.3094. Min Act: -0.1700
Data Index: 4457874 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.3094. Min Act: -0.1699
Data Index: 3090540 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.2781. Min Act: -0.1700
Data Index: 6860688 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.3094. Min Act: -0.1700
Data Index: 3471591 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5594. Min Range: -5.5594
Max Act: 5.2781. Min Act: -0.1700
Data Index: 6081376 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19