Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0647. Min Range: -4.0647
Max Act: 4.0647. Min Act: -0.1700
Data Index: 6119350 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0647. Min Range: -4.0647
Max Act: 4.0022. Min Act: -0.1700
Data Index: 3503703 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0647. Min Range: -4.0647
Max Act: 4.0335. Min Act: -0.1700
Data Index: 4265574 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.9709. Min Act: -0.1700
Data Index: 3503702 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.9709. Min Act: -0.1700
Data Index: 4391595 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.9709. Min Act: -0.1700
Data Index: 6211760 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.9397. Min Act: -0.1700
Data Index: 3639186 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.9084. Min Act: -0.1700
Data Index: 444425 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.9397. Min Act: -0.1700
Data Index: 6432661 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.9084. Min Act: -0.1700
Data Index: 3617060 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.8771. Min Act: -0.1700
Data Index: 7916888 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.8771. Min Act: -0.1700
Data Index: 415566 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.8459. Min Act: -0.1700
Data Index: 2163942 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.8459. Min Act: -0.1700
Data Index: 6177995 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.8459. Min Act: -0.1700
Data Index: 8674289 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.8146. Min Act: -0.1700
Data Index: 603470 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.8146. Min Act: -0.1700
Data Index: 1834600 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.7833. Min Act: -0.1700
Data Index: 2277160 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.8146. Min Act: -0.1700
Data Index: 8116823 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0647. Min Range: -4.0647
Max Act: 3.7833. Min Act: -0.1700
Data Index: 659191 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19