Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5479 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.4994. Min Act: -0.1700
Data Index: 6489248 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.4369. Min Act: -0.1700
Data Index: 3439405 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.4369. Min Act: -0.1700
Data Index: 3687090 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.2807. Min Act: -0.1700
Data Index: 4546414 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.2182. Min Act: -0.1700
Data Index: 5381070 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.2182. Min Act: -0.1700
Data Index: 5586222 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.2494. Min Act: -0.1700
Data Index: 6724062 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.2182. Min Act: -0.1700
Data Index: 855875 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.2182. Min Act: -0.1700
Data Index: 7549804 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.1869. Min Act: -0.1700
Data Index: 4265275 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.2182. Min Act: -0.1700
Data Index: 5468118 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.2182. Min Act: -0.1700
Data Index: 3710387 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.1244. Min Act: -0.1700
Data Index: 5828177 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.1244. Min Act: -0.1700
Data Index: 2425161 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.0932. Min Act: -0.1700
Data Index: 6486378 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.0932. Min Act: -0.1700
Data Index: 2028047 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.0619. Min Act: -0.1700
Data Index: 1900234 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.0307. Min Act: -0.1700
Data Index: 4569278 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4994. Min Range: -6.4994
Max Act: 6.0307. Min Act: -0.1700
Data Index: 2963204 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4994. Min Range: -6.4994
Max Act: 5.9994. Min Act: -0.1700
Data Index: 2015587 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19