Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2393 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2770. Min Range: -7.2770
Max Act: 7.2770. Min Act: -0.1700
Data Index: 7282919 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2770. Min Range: -7.2770
Max Act: 7.2457. Min Act: -0.1700
Data Index: 3131126 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2770. Min Range: -7.2770
Max Act: 7.2145. Min Act: -0.1700
Data Index: 2706200 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2770. Min Range: -7.2770
Max Act: 7.0895. Min Act: -0.1700
Data Index: 5540104 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2770. Min Range: -7.2770
Max Act: 7.0270. Min Act: -0.1700
Data Index: 2059378 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2770. Min Range: -7.2770
Max Act: 7.0270. Min Act: -0.1700
Data Index: 6461763 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2770. Min Range: -7.2770
Max Act: 7.0270. Min Act: -0.1700
Data Index: 6620722 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9957. Min Act: -0.1700
Data Index: 4565362 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2770. Min Range: -7.2770
Max Act: 7.0270. Min Act: -0.1700
Data Index: 8356233 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2770. Min Range: -7.2770
Max Act: 7.0270. Min Act: -0.1700
Data Index: 8006391 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9957. Min Act: -0.1700
Data Index: 897639 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9645. Min Act: -0.1700
Data Index: 4823233 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9645. Min Act: -0.1700
Data Index: 3169151 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9645. Min Act: -0.1700
Data Index: 6102900 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9645. Min Act: -0.1700
Data Index: 5931962 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9020. Min Act: -0.1700
Data Index: 3840041 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9020. Min Act: -0.1700
Data Index: 5470389 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9020. Min Act: -0.1700
Data Index: 4934248 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9332. Min Act: -0.1700
Data Index: 7366473 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9020. Min Act: -0.1700
Data Index: 6062351 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19