Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.6822. Min Act: -0.1700
Data Index: 5346111 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.5572. Min Act: -0.1700
Data Index: 7772449 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.5259. Min Act: -0.1700
Data Index: 5882475 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.3384. Min Act: -0.1700
Data Index: 4546863 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.2759. Min Act: -0.1700
Data Index: 6724747 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.2759. Min Act: -0.1700
Data Index: 5898171 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.2759. Min Act: -0.1700
Data Index: 5346109 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.3072. Min Act: -0.1700
Data Index: 2937367 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.2759. Min Act: -0.1700
Data Index: 7836152 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.2447. Min Act: -0.1700
Data Index: 5898172 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.2134. Min Act: -0.1700
Data Index: 6921155 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.2134. Min Act: -0.1700
Data Index: 5792004 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.1822. Min Act: -0.1700
Data Index: 6724745 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.1822. Min Act: -0.1700
Data Index: 6724743 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.1822. Min Act: -0.1700
Data Index: 6724744 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.1509. Min Act: -0.1700
Data Index: 5898173 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.1509. Min Act: -0.1700
Data Index: 776282 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.1197. Min Act: -0.1700
Data Index: 6724746 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.0884. Min Act: -0.1700
Data Index: 4154089 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.0884. Min Act: -0.1700
Data Index: 5543249 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19