Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.4332. Min Act: -0.1700
Data Index: 5371881 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.4645. Min Act: -0.1700
Data Index: 5346975 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.4332. Min Act: -0.1700
Data Index: 5155114 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.4020. Min Act: -0.1700
Data Index: 806190 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.4020. Min Act: -0.1700
Data Index: 256448 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.3707. Min Act: -0.1700
Data Index: 1924585 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.3082. Min Act: -0.1700
Data Index: 5550897 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.3082. Min Act: -0.1700
Data Index: 5141050 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.2770. Min Act: -0.1700
Data Index: 8543872 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.3082. Min Act: -0.1700
Data Index: 693009 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.2770. Min Act: -0.1700
Data Index: 7551022 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.3082. Min Act: -0.1700
Data Index: 2706674 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.2770. Min Act: -0.1700
Data Index: 5887191 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.2770. Min Act: -0.1700
Data Index: 2571637 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.2457. Min Act: -0.1700
Data Index: 5660423 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.1832. Min Act: -0.1700
Data Index: 4709484 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.2145. Min Act: -0.1700
Data Index: 3484468 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.1207. Min Act: -0.1700
Data Index: 4748052 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.1832. Min Act: -0.1700
Data Index: 4964266 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4645. Min Range: -5.4645
Max Act: 5.1207. Min Act: -0.1700
Data Index: 6585090 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19