Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2268 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.3776. Min Act: -0.1700
Data Index: 7327792 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.3305. Min Act: -0.1700
Data Index: 5818370 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.2991. Min Act: -0.1700
Data Index: 5918298 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.2834. Min Act: -0.1700
Data Index: 5538404 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.2834. Min Act: -0.1700
Data Index: 2806955 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.2677. Min Act: -0.1700
Data Index: 62944 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.2520. Min Act: -0.1700
Data Index: 7527384 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.2363. Min Act: -0.1700
Data Index: 1346115 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.2206. Min Act: -0.1700
Data Index: 205383 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.2048. Min Act: -0.1700
Data Index: 61567 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.1576. Min Act: -0.1700
Data Index: 3473944 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.1734. Min Act: -0.1700
Data Index: 2261693 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.1734. Min Act: -0.1700
Data Index: 352630 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.1576. Min Act: -0.1700
Data Index: 8099035 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.1734. Min Act: -0.1700
Data Index: 4314580 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.1419. Min Act: -0.1700
Data Index: 2362971 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.1419. Min Act: -0.1700
Data Index: 7592887 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.1419. Min Act: -0.1700
Data Index: 2753658 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.1419. Min Act: -0.1700
Data Index: 6892113 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3776. Min Range: -3.3776
Max Act: 3.1262. Min Act: -0.1700
Data Index: 2648002 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19