Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4328 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.6774. Min Act: -0.1700
Data Index: 1707705 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.6774. Min Act: -0.1700
Data Index: 7857030 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.5991. Min Act: -0.1700
Data Index: 8344560 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.6148. Min Act: -0.1700
Data Index: 915352 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.5835. Min Act: -0.1700
Data Index: 7372330 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.5678. Min Act: -0.1700
Data Index: 5839100 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.5678. Min Act: -0.1700
Data Index: 8346038 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.5678. Min Act: -0.1700
Data Index: 5772657 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.5365. Min Act: -0.1700
Data Index: 7565150 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.5365. Min Act: -0.1700
Data Index: 1938664 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.5522. Min Act: -0.1700
Data Index: 2571760 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.5209. Min Act: -0.1700
Data Index: 8168912 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.5052. Min Act: -0.1700
Data Index: 3472171 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.5052. Min Act: -0.1700
Data Index: 6047089 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.4895. Min Act: -0.1700
Data Index: 4184709 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.5052. Min Act: -0.1700
Data Index: 1856282 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.4739. Min Act: -0.1700
Data Index: 2620656 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.4739. Min Act: -0.1700
Data Index: 5148024 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.4582. Min Act: -0.1700
Data Index: 1143293 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6774. Min Range: -3.6774
Max Act: 3.4582. Min Act: -0.1700
Data Index: 6454836 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19