Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4850 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2186. Min Range: -6.2186
Max Act: 6.2186. Min Act: -0.1700
Data Index: 3765182 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2186. Min Range: -6.2186
Max Act: 6.0936. Min Act: -0.1700
Data Index: 3330062 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.7811. Min Act: -0.1700
Data Index: 6358801 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.7811. Min Act: -0.1700
Data Index: 3701131 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.7498. Min Act: -0.1700
Data Index: 2505067 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.6873. Min Act: -0.1700
Data Index: 4057736 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.6561. Min Act: -0.1700
Data Index: 3295693 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.5936. Min Act: -0.1700
Data Index: 389000 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.5936. Min Act: -0.1700
Data Index: 7076372 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.5311. Min Act: -0.1700
Data Index: 5797838 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.5311. Min Act: -0.1700
Data Index: 4350325 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.4998. Min Act: -0.1700
Data Index: 6308967 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.4998. Min Act: -0.1700
Data Index: 4217440 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.4686. Min Act: -0.1700
Data Index: 5851031 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.4998. Min Act: -0.1700
Data Index: 6909162 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.4686. Min Act: -0.1700
Data Index: 8376542 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.4373. Min Act: -0.1700
Data Index: 1924302 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.4686. Min Act: -0.1700
Data Index: 3097086 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.4373. Min Act: -0.1700
Data Index: 1927710 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2186. Min Range: -6.2186
Max Act: 5.4061. Min Act: -0.1700
Data Index: 4183510 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19