Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2798 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.7289. Min Act: -0.1700
Data Index: 6792952 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.7289. Min Act: -0.1700
Data Index: 3429500 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.7289. Min Act: -0.1700
Data Index: 977755 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.7289. Min Act: -0.1700
Data Index: 5791338 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.7289. Min Act: -0.1700
Data Index: 1563027 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.7289. Min Act: -0.1700
Data Index: 6641841 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.6664. Min Act: -0.1700
Data Index: 3685855 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.6664. Min Act: -0.1700
Data Index: 5782430 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.6664. Min Act: -0.1700
Data Index: 655986 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.6664. Min Act: -0.1700
Data Index: 1581537 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.6664. Min Act: -0.1700
Data Index: 8167965 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.6664. Min Act: -0.1700
Data Index: 7910038 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.6664. Min Act: -0.1700
Data Index: 7270192 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.6039. Min Act: -0.1700
Data Index: 3678740 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.6664. Min Act: -0.1700
Data Index: 1743050 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.6039. Min Act: -0.1700
Data Index: 5702256 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.6039. Min Act: -0.1700
Data Index: 381624 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.6039. Min Act: -0.1700
Data Index: 237592 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.6039. Min Act: -0.1700
Data Index: 6188381 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7289. Min Range: -6.7289
Max Act: 6.6039. Min Act: -0.1700
Data Index: 1442206 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19