Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4253 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.8352. Min Act: -0.1700
Data Index: 4054493 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.8039. Min Act: -0.1700
Data Index: 1443779 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.7414. Min Act: -0.1700
Data Index: 5859067 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.6789. Min Act: -0.1700
Data Index: 3578535 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.5227. Min Act: -0.1700
Data Index: 6179091 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.5539. Min Act: -0.1700
Data Index: 2967108 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.5539. Min Act: -0.1700
Data Index: 7487287 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.4914. Min Act: -0.1700
Data Index: 5507909 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.4602. Min Act: -0.1700
Data Index: 6714025 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.4289. Min Act: -0.1700
Data Index: 593437 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.3977. Min Act: -0.1700
Data Index: 3126192 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.3977. Min Act: -0.1700
Data Index: 1602195 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.3664. Min Act: -0.1700
Data Index: 3333527 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.3352. Min Act: -0.1700
Data Index: 1129558 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.3039. Min Act: -0.1700
Data Index: 3960778 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.3039. Min Act: -0.1700
Data Index: 3524684 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.3352. Min Act: -0.1700
Data Index: 458151 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.2727. Min Act: -0.1700
Data Index: 2532096 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.3039. Min Act: -0.1700
Data Index: 2260163 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8352. Min Range: -6.8352
Max Act: 6.2727. Min Act: -0.1700
Data Index: 6339923 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19