Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1159 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.9624. Min Act: -0.1700
Data Index: 5732868 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.4936. Min Act: -0.1700
Data Index: 3424036 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.4936. Min Act: -0.1700
Data Index: 1546215 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.4311. Min Act: -0.1700
Data Index: 4750009 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.3686. Min Act: -0.1700
Data Index: 7975521 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.3686. Min Act: -0.1700
Data Index: 5125032 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.3686. Min Act: -0.1700
Data Index: 2622823 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.3686. Min Act: -0.1700
Data Index: 8275272 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.3374. Min Act: -0.1700
Data Index: 3775779 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.3061. Min Act: -0.1700
Data Index: 4285599 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.3374. Min Act: -0.1700
Data Index: 3220155 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.2749. Min Act: -0.1700
Data Index: 8012600 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.2749. Min Act: -0.1700
Data Index: 432232 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.2749. Min Act: -0.1700
Data Index: 6195048 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.2436. Min Act: -0.1700
Data Index: 4347795 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.2436. Min Act: -0.1700
Data Index: 5292859 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.2436. Min Act: -0.1700
Data Index: 710348 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.2124. Min Act: -0.1700
Data Index: 8231597 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.1811. Min Act: -0.1700
Data Index: 4907733 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9624. Min Range: -5.9624
Max Act: 5.2124. Min Act: -0.1700
Data Index: 5746342 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19