Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2962 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.5239. Min Act: -0.1700
Data Index: 5213175 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.4926. Min Act: -0.1700
Data Index: 3291710 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.4926. Min Act: -0.1700
Data Index: 4600495 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.4769. Min Act: -0.1700
Data Index: 933120 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.5083. Min Act: -0.1700
Data Index: 79046 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.4769. Min Act: -0.1700
Data Index: 3086339 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.4613. Min Act: -0.1700
Data Index: 3965672 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.4613. Min Act: -0.1700
Data Index: 7769045 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.4456. Min Act: -0.1700
Data Index: 1467513 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.4613. Min Act: -0.1700
Data Index: 4064376 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.4456. Min Act: -0.1700
Data Index: 62160 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.4299. Min Act: -0.1700
Data Index: 7934359 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.4299. Min Act: -0.1700
Data Index: 7710327 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.4143. Min Act: -0.1700
Data Index: 7565114 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.3986. Min Act: -0.1700
Data Index: 964546 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.3829. Min Act: -0.1700
Data Index: 7769048 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.3986. Min Act: -0.1700
Data Index: 2792110 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.3358. Min Act: -0.1700
Data Index: 247301 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.3515. Min Act: -0.1700
Data Index: 4911609 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5239. Min Range: -3.5239
Max Act: 3.3358. Min Act: -0.1700
Data Index: 5846806 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19