Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4352 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.8754. Min Act: -0.1700
Data Index: 5048859 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.8442. Min Act: -0.1700
Data Index: 3684590 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.8442. Min Act: -0.1700
Data Index: 2180219 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.8129. Min Act: -0.1700
Data Index: 3866542 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.7817. Min Act: -0.1700
Data Index: 4219622 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.7817. Min Act: -0.1700
Data Index: 3289213 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.7192. Min Act: -0.1700
Data Index: 2691859 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.6567. Min Act: -0.1700
Data Index: 6138951 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.6254. Min Act: -0.1700
Data Index: 6122746 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.6254. Min Act: -0.1700
Data Index: 5879268 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.5942. Min Act: -0.1700
Data Index: 526920 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.5942. Min Act: -0.1700
Data Index: 3937939 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.5629. Min Act: -0.1700
Data Index: 4972547 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.5004. Min Act: -0.1700
Data Index: 6546781 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.5317. Min Act: -0.1700
Data Index: 2472851 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.5629. Min Act: -0.1700
Data Index: 2133109 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.4692. Min Act: -0.1700
Data Index: 5293925 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.4692. Min Act: -0.1700
Data Index: 1824337 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.5004. Min Act: -0.1700
Data Index: 2159453 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8754. Min Range: -6.8754
Max Act: 6.4692. Min Act: -0.1700
Data Index: 891371 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19