Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 218 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6863. Min Range: -7.6863
Max Act: 7.6863. Min Act: -0.1700
Data Index: 349147 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6863. Min Range: -7.6863
Max Act: 7.6550. Min Act: -0.1700
Data Index: 2093957 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6863. Min Range: -7.6863
Max Act: 7.5300. Min Act: -0.1700
Data Index: 3954049 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6863. Min Range: -7.6863
Max Act: 7.4050. Min Act: -0.1700
Data Index: 7332625 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6863. Min Range: -7.6863
Max Act: 7.3738. Min Act: -0.1700
Data Index: 543645 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6863. Min Range: -7.6863
Max Act: 7.3425. Min Act: -0.1700
Data Index: 6441755 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6863. Min Range: -7.6863
Max Act: 7.2175. Min Act: -0.1700
Data Index: 301087 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6863. Min Range: -7.6863
Max Act: 7.2488. Min Act: -0.1700
Data Index: 4563174 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6863. Min Range: -7.6863
Max Act: 7.1550. Min Act: -0.1700
Data Index: 2308476 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6863. Min Range: -7.6863
Max Act: 7.1238. Min Act: -0.1700
Data Index: 8596118 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6863. Min Range: -7.6863
Max Act: 7.0613. Min Act: -0.1700
Data Index: 907404 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6863. Min Range: -7.6863
Max Act: 7.0300. Min Act: -0.1700
Data Index: 635896 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6863. Min Range: -7.6863
Max Act: 7.0300. Min Act: -0.1700
Data Index: 5721534 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6863. Min Range: -7.6863
Max Act: 7.0300. Min Act: -0.1700
Data Index: 8315162 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6863. Min Range: -7.6863
Max Act: 6.9988. Min Act: -0.1700
Data Index: 7387695 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6863. Min Range: -7.6863
Max Act: 6.9988. Min Act: -0.1700
Data Index: 7341180 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6863. Min Range: -7.6863
Max Act: 6.9675. Min Act: -0.1700
Data Index: 7091896 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6863. Min Range: -7.6863
Max Act: 6.9675. Min Act: -0.1700
Data Index: 4077626 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6863. Min Range: -7.6863
Max Act: 6.9988. Min Act: -0.1700
Data Index: 8575341 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6863. Min Range: -7.6863
Max Act: 6.9988. Min Act: -0.1700
Data Index: 1547707 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19