Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3748 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7141. Min Range: -6.7141
Max Act: 6.7141. Min Act: -0.1700
Data Index: 1100945 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7141. Min Range: -6.7141
Max Act: 6.6516. Min Act: -0.1700
Data Index: 4935900 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7141. Min Range: -6.7141
Max Act: 6.5266. Min Act: -0.1700
Data Index: 3319917 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7141. Min Range: -6.7141
Max Act: 6.3391. Min Act: -0.1700
Data Index: 6878448 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7141. Min Range: -6.7141
Max Act: 6.3391. Min Act: -0.1700
Data Index: 41605 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7141. Min Range: -6.7141
Max Act: 6.1203. Min Act: -0.1700
Data Index: 2134363 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7141. Min Range: -6.7141
Max Act: 6.0891. Min Act: -0.1700
Data Index: 4964968 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7141. Min Range: -6.7141
Max Act: 6.1203. Min Act: -0.1700
Data Index: 1614868 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7141. Min Range: -6.7141
Max Act: 5.9953. Min Act: -0.1700
Data Index: 7353467 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7141. Min Range: -6.7141
Max Act: 5.9953. Min Act: -0.1700
Data Index: 1086860 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7141. Min Range: -6.7141
Max Act: 5.9641. Min Act: -0.1700
Data Index: 2120626 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7141. Min Range: -6.7141
Max Act: 5.9641. Min Act: -0.1700
Data Index: 588509 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7141. Min Range: -6.7141
Max Act: 5.9641. Min Act: -0.1700
Data Index: 5710008 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7141. Min Range: -6.7141
Max Act: 5.9328. Min Act: -0.1700
Data Index: 2643239 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7141. Min Range: -6.7141
Max Act: 5.9328. Min Act: -0.1700
Data Index: 6796180 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7141. Min Range: -6.7141
Max Act: 5.9328. Min Act: -0.1700
Data Index: 362662 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7141. Min Range: -6.7141
Max Act: 5.9328. Min Act: -0.1700
Data Index: 7191374 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7141. Min Range: -6.7141
Max Act: 5.9328. Min Act: -0.1700
Data Index: 3864056 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7141. Min Range: -6.7141
Max Act: 5.9328. Min Act: -0.1700
Data Index: 2251730 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7141. Min Range: -6.7141
Max Act: 5.9328. Min Act: -0.1700
Data Index: 3041838 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19