Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2000 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.4138. Min Act: -0.1700
Data Index: 5229579 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.4450. Min Act: -0.1700
Data Index: 1066571 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.2888. Min Act: -0.1700
Data Index: 1945806 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.3200. Min Act: -0.1700
Data Index: 2224784 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.2263. Min Act: -0.1700
Data Index: 4080764 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.2263. Min Act: -0.1700
Data Index: 8796954 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.1638. Min Act: -0.1700
Data Index: 7689914 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.1013. Min Act: -0.1700
Data Index: 1301032 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.0700. Min Act: -0.1700
Data Index: 3980290 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.9450. Min Act: -0.1700
Data Index: 5809867 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.9450. Min Act: -0.1700
Data Index: 4699769 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.9138. Min Act: -0.1700
Data Index: 3134671 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.9450. Min Act: -0.1700
Data Index: 1094183 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.9138. Min Act: -0.1700
Data Index: 2609268 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.9138. Min Act: -0.1700
Data Index: 6758020 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.9138. Min Act: -0.1700
Data Index: 1138134 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.9138. Min Act: -0.1700
Data Index: 4268070 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.8825. Min Act: -0.1700
Data Index: 8179605 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.8825. Min Act: -0.1700
Data Index: 7181785 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.8200. Min Act: -0.1700
Data Index: 5244796 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19