Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5136 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.2729. Min Act: -0.1700
Data Index: 4624827 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.2729. Min Act: -0.1700
Data Index: 6392284 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.2104. Min Act: -0.1700
Data Index: 4924081 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.1166. Min Act: -0.1700
Data Index: 1834363 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0228. Min Act: -0.1700
Data Index: 4161100 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0228. Min Act: -0.1700
Data Index: 1355702 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0228. Min Act: -0.1700
Data Index: 2654198 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0228. Min Act: -0.1700
Data Index: 7040053 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0228. Min Act: -0.1700
Data Index: 3332416 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.9916. Min Act: -0.1700
Data Index: 4342083 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.9916. Min Act: -0.1700
Data Index: 4720587 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.9916. Min Act: -0.1700
Data Index: 8777677 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.9603. Min Act: -0.1700
Data Index: 2782158 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.9603. Min Act: -0.1700
Data Index: 4187261 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.9290. Min Act: -0.1700
Data Index: 3755836 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.9290. Min Act: -0.1700
Data Index: 1942572 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.8978. Min Act: -0.1700
Data Index: 3396300 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.8978. Min Act: -0.1700
Data Index: 2551701 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.8978. Min Act: -0.1700
Data Index: 5975467 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.8665. Min Act: -0.1700
Data Index: 5962853 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19