Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5910 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4336. Min Range: -7.4336
Max Act: 7.4336. Min Act: -0.1700
Data Index: 2331489 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4336. Min Range: -7.4336
Max Act: 7.2774. Min Act: -0.1700
Data Index: 7381875 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4336. Min Range: -7.4336
Max Act: 7.2149. Min Act: -0.1700
Data Index: 5101325 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4336. Min Range: -7.4336
Max Act: 7.1524. Min Act: -0.1700
Data Index: 6157840 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4336. Min Range: -7.4336
Max Act: 7.1211. Min Act: -0.1700
Data Index: 4890343 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4336. Min Range: -7.4336
Max Act: 7.0899. Min Act: -0.1700
Data Index: 471749 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4336. Min Range: -7.4336
Max Act: 7.0586. Min Act: -0.1700
Data Index: 837321 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4336. Min Range: -7.4336
Max Act: 7.0586. Min Act: -0.1700
Data Index: 3729997 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4336. Min Range: -7.4336
Max Act: 7.0274. Min Act: -0.1700
Data Index: 6571089 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4336. Min Range: -7.4336
Max Act: 7.0274. Min Act: -0.1700
Data Index: 6282412 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4336. Min Range: -7.4336
Max Act: 7.0274. Min Act: -0.1700
Data Index: 5389402 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4336. Min Range: -7.4336
Max Act: 7.0274. Min Act: -0.1700
Data Index: 7655657 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4336. Min Range: -7.4336
Max Act: 6.9961. Min Act: -0.1700
Data Index: 6561751 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4336. Min Range: -7.4336
Max Act: 6.9961. Min Act: -0.1700
Data Index: 1498677 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4336. Min Range: -7.4336
Max Act: 6.9336. Min Act: -0.1700
Data Index: 7578294 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4336. Min Range: -7.4336
Max Act: 6.9336. Min Act: -0.1700
Data Index: 1453044 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4336. Min Range: -7.4336
Max Act: 6.9336. Min Act: -0.1700
Data Index: 5615369 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4336. Min Range: -7.4336
Max Act: 6.9024. Min Act: -0.1700
Data Index: 2681061 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4336. Min Range: -7.4336
Max Act: 6.8711. Min Act: -0.1700
Data Index: 606449 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4336. Min Range: -7.4336
Max Act: 6.8711. Min Act: -0.1700
Data Index: 6836508 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19