Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3935 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.6897. Min Act: -0.1700
Data Index: 149027 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.6584. Min Act: -0.1700
Data Index: 3952610 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.5334. Min Act: -0.1700
Data Index: 1930482 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.4397. Min Act: -0.1700
Data Index: 4003982 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.3147. Min Act: -0.1700
Data Index: 1325608 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.3147. Min Act: -0.1700
Data Index: 4725172 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.1272. Min Act: -0.1700
Data Index: 4748268 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.1272. Min Act: -0.1700
Data Index: 1321695 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.0959. Min Act: -0.1700
Data Index: 8259815 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.0647. Min Act: -0.1700
Data Index: 7859620 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.0334. Min Act: -0.1700
Data Index: 8460122 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.0022. Min Act: -0.1700
Data Index: 1537775 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.0022. Min Act: -0.1700
Data Index: 2288229 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.0334. Min Act: -0.1700
Data Index: 3773474 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6897. Min Range: -7.6897
Max Act: 7.0022. Min Act: -0.1700
Data Index: 1010619 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6897. Min Range: -7.6897
Max Act: 6.9709. Min Act: -0.1700
Data Index: 7603426 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6897. Min Range: -7.6897
Max Act: 6.9709. Min Act: -0.1700
Data Index: 6290692 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6897. Min Range: -7.6897
Max Act: 6.9397. Min Act: -0.1700
Data Index: 1772493 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6897. Min Range: -7.6897
Max Act: 6.9397. Min Act: -0.1700
Data Index: 1358449 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6897. Min Range: -7.6897
Max Act: 6.9397. Min Act: -0.1700
Data Index: 6964333 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19