Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4571 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.9161. Min Act: -0.1700
Data Index: 4697190 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.7286. Min Act: -0.1700
Data Index: 138004 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.6349. Min Act: -0.1700
Data Index: 3208412 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.6349. Min Act: -0.1700
Data Index: 6763447 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.6349. Min Act: -0.1700
Data Index: 6354840 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.6349. Min Act: -0.1700
Data Index: 8728176 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.6349. Min Act: -0.1700
Data Index: 4243161 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.5411. Min Act: -0.1700
Data Index: 7667118 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.5099. Min Act: -0.1700
Data Index: 3900789 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.5724. Min Act: -0.1700
Data Index: 8630889 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.5411. Min Act: -0.1700
Data Index: 4669739 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.5099. Min Act: -0.1700
Data Index: 2296608 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.5099. Min Act: -0.1700
Data Index: 6921449 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.5411. Min Act: -0.1700
Data Index: 138001 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.5099. Min Act: -0.1700
Data Index: 5808928 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.5099. Min Act: -0.1700
Data Index: 3722645 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.4786. Min Act: -0.1700
Data Index: 138002 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.4786. Min Act: -0.1700
Data Index: 8499556 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.4474. Min Act: -0.1700
Data Index: 514238 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9161. Min Range: -5.9161
Max Act: 5.4474. Min Act: -0.1700
Data Index: 673312 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19