Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0140. Min Range: -4.0140
Max Act: 4.0140. Min Act: -0.1700
Data Index: 6083072 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.9515. Min Act: -0.1700
Data Index: 1812312 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.9515. Min Act: -0.1700
Data Index: 8749841 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.9515. Min Act: -0.1700
Data Index: 6447935 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.9202. Min Act: -0.1700
Data Index: 3427781 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.8889. Min Act: -0.1700
Data Index: 686649 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.8577. Min Act: -0.1700
Data Index: 3721398 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.8577. Min Act: -0.1700
Data Index: 310382 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.8577. Min Act: -0.1700
Data Index: 4388323 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.8264. Min Act: -0.1700
Data Index: 167565 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.8264. Min Act: -0.1700
Data Index: 6945067 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.8264. Min Act: -0.1700
Data Index: 87075 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.7951. Min Act: -0.1700
Data Index: 7462120 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.7951. Min Act: -0.1700
Data Index: 3873671 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.7951. Min Act: -0.1700
Data Index: 8435445 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.7951. Min Act: -0.1700
Data Index: 2312756 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.7951. Min Act: -0.1700
Data Index: 7589658 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.7951. Min Act: -0.1700
Data Index: 3679154 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.7951. Min Act: -0.1700
Data Index: 4976290 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0140. Min Range: -4.0140
Max Act: 3.7638. Min Act: -0.1700
Data Index: 2513640 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19