Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2101. Min Range: -3.2101
Max Act: 3.2101. Min Act: -0.1700
Data Index: 2441875 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.8150. Min Act: -0.1700
Data Index: 3111949 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.7832. Min Act: -0.1700
Data Index: 2441874 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.7672. Min Act: -0.1700
Data Index: 5599812 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.7513. Min Act: -0.1700
Data Index: 4349328 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.7033. Min Act: -0.1700
Data Index: 6262641 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.6873. Min Act: -0.1700
Data Index: 8548429 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.6392. Min Act: -0.1700
Data Index: 1917370 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.6232. Min Act: -0.1700
Data Index: 3111950 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.6071. Min Act: -0.1700
Data Index: 2080586 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.5910. Min Act: -0.1700
Data Index: 7108554 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.5910. Min Act: -0.1700
Data Index: 5628203 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.5749. Min Act: -0.1700
Data Index: 4576757 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.5749. Min Act: -0.1700
Data Index: 4415762 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.5587. Min Act: -0.1700
Data Index: 2441873 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.5426. Min Act: -0.1700
Data Index: 4938763 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.5264. Min Act: -0.1700
Data Index: 3379848 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.5426. Min Act: -0.1700
Data Index: 4601270 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.5264. Min Act: -0.1700
Data Index: 2005990 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2101. Min Range: -3.2101
Max Act: 2.5103. Min Act: -0.1700
Data Index: 2451767 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19