Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4403 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.7957. Min Act: -0.1700
Data Index: 6487627 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.4832. Min Act: -0.1700
Data Index: 4092088 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.4519. Min Act: -0.1700
Data Index: 7346621 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.4207. Min Act: -0.1700
Data Index: 5754894 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.3269. Min Act: -0.1700
Data Index: 5396606 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2957. Min Act: -0.1700
Data Index: 8648517 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2957. Min Act: -0.1700
Data Index: 8002729 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2957. Min Act: -0.1700
Data Index: 3341237 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2957. Min Act: -0.1700
Data Index: 7853159 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2644. Min Act: -0.1700
Data Index: 6352105 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2644. Min Act: -0.1700
Data Index: 5139622 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2644. Min Act: -0.1700
Data Index: 7150153 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2332. Min Act: -0.1700
Data Index: 154813 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2644. Min Act: -0.1700
Data Index: 1144008 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2019. Min Act: -0.1700
Data Index: 3388780 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2019. Min Act: -0.1700
Data Index: 7912715 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2019. Min Act: -0.1700
Data Index: 7411460 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2019. Min Act: -0.1700
Data Index: 1361858 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2019. Min Act: -0.1700
Data Index: 851767 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.2019. Min Act: -0.1700
Data Index: 807239 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19