Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2203 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.9855. Min Act: -0.1700
Data Index: 4895746 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.7668. Min Act: -0.1700
Data Index: 1242966 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.7668. Min Act: -0.1700
Data Index: 795474 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.6418. Min Act: -0.1700
Data Index: 4913069 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.6105. Min Act: -0.1700
Data Index: 7736924 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.6418. Min Act: -0.1700
Data Index: 5672310 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.5793. Min Act: -0.1700
Data Index: 6607558 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.5480. Min Act: -0.1700
Data Index: 5022756 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.5480. Min Act: -0.1700
Data Index: 4696608 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.5480. Min Act: -0.1700
Data Index: 1601565 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.5480. Min Act: -0.1700
Data Index: 2770974 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.5168. Min Act: -0.1700
Data Index: 2681056 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.4855. Min Act: -0.1700
Data Index: 938147 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.5168. Min Act: -0.1700
Data Index: 1117914 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.4855. Min Act: -0.1700
Data Index: 1715969 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.4543. Min Act: -0.1700
Data Index: 2372364 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.4855. Min Act: -0.1700
Data Index: 3207962 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.4855. Min Act: -0.1700
Data Index: 5775500 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.4543. Min Act: -0.1700
Data Index: 6454873 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.4543. Min Act: -0.1700
Data Index: 1019632 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19