Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1789 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.7343. Min Act: -0.1700
Data Index: 104791 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.7031. Min Act: -0.1700
Data Index: 1468292 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.6406. Min Act: -0.1700
Data Index: 6661274 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.6406. Min Act: -0.1700
Data Index: 2906191 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.6093. Min Act: -0.1700
Data Index: 8282924 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.6406. Min Act: -0.1700
Data Index: 824524 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.6406. Min Act: -0.1700
Data Index: 4142588 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.6093. Min Act: -0.1700
Data Index: 4545130 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.5468. Min Act: -0.1700
Data Index: 7268614 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.5468. Min Act: -0.1700
Data Index: 8215964 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.5468. Min Act: -0.1700
Data Index: 7113302 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.5156. Min Act: -0.1700
Data Index: 7593987 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.5156. Min Act: -0.1700
Data Index: 7524040 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.4531. Min Act: -0.1700
Data Index: 574491 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.4843. Min Act: -0.1700
Data Index: 8182723 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.4843. Min Act: -0.1700
Data Index: 8662117 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.4531. Min Act: -0.1700
Data Index: 3027786 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.4531. Min Act: -0.1700
Data Index: 5071996 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.4531. Min Act: -0.1700
Data Index: 4454388 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7343. Min Range: -7.7343
Max Act: 7.4218. Min Act: -0.1700
Data Index: 3053 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19