Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2840 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1341. Min Range: -5.1341
Max Act: 5.1341. Min Act: -0.1700
Data Index: 3554734 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.9779. Min Act: -0.1700
Data Index: 4145177 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.9779. Min Act: -0.1700
Data Index: 7653715 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.9466. Min Act: -0.1700
Data Index: 4328811 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.9466. Min Act: -0.1700
Data Index: 4313949 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.9466. Min Act: -0.1700
Data Index: 4944700 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.9466. Min Act: -0.1700
Data Index: 3776316 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.9154. Min Act: -0.1700
Data Index: 161291 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.9154. Min Act: -0.1700
Data Index: 5718647 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.9154. Min Act: -0.1700
Data Index: 4241702 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.9154. Min Act: -0.1700
Data Index: 335237 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.9154. Min Act: -0.1700
Data Index: 7457113 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.9154. Min Act: -0.1700
Data Index: 3687093 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.8841. Min Act: -0.1700
Data Index: 4697579 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.8841. Min Act: -0.1700
Data Index: 5461433 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.8841. Min Act: -0.1700
Data Index: 8353214 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.8841. Min Act: -0.1700
Data Index: 4263276 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.8841. Min Act: -0.1700
Data Index: 3122735 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.8529. Min Act: -0.1700
Data Index: 4835200 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1341. Min Range: -5.1341
Max Act: 4.8529. Min Act: -0.1700
Data Index: 3267274 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19