Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.7822. Min Act: -0.1700
Data Index: 8769955 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.6259. Min Act: -0.1700
Data Index: 7870001 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.5634. Min Act: -0.1700
Data Index: 436178 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.4384. Min Act: -0.1700
Data Index: 6060520 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.3759. Min Act: -0.1700
Data Index: 3377940 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.3759. Min Act: -0.1700
Data Index: 2320430 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.2822. Min Act: -0.1700
Data Index: 7869988 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.2509. Min Act: -0.1700
Data Index: 2710926 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.2197. Min Act: -0.1700
Data Index: 5785704 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.2509. Min Act: -0.1700
Data Index: 2930259 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.2197. Min Act: -0.1700
Data Index: 7514570 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.1884. Min Act: -0.1700
Data Index: 7978641 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.1259. Min Act: -0.1700
Data Index: 1641116 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.1259. Min Act: -0.1700
Data Index: 8186444 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.1259. Min Act: -0.1700
Data Index: 3448520 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.0634. Min Act: -0.1700
Data Index: 2670699 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.1259. Min Act: -0.1700
Data Index: 1627910 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.0634. Min Act: -0.1700
Data Index: 921566 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.0634. Min Act: -0.1700
Data Index: 1807493 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7822. Min Range: -5.7822
Max Act: 5.0322. Min Act: -0.1700
Data Index: 2112857 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19