Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2494 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.2770. Min Act: -0.1700
Data Index: 2208263 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.2770. Min Act: -0.1700
Data Index: 5681254 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.2457. Min Act: -0.1700
Data Index: 8261885 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.2145. Min Act: -0.1700
Data Index: 7385939 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.2145. Min Act: -0.1700
Data Index: 893624 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.2145. Min Act: -0.1700
Data Index: 8337254 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.2145. Min Act: -0.1700
Data Index: 8254841 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.2145. Min Act: -0.1700
Data Index: 7979802 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.2145. Min Act: -0.1700
Data Index: 7385938 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1832. Min Act: -0.1700
Data Index: 4612380 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1832. Min Act: -0.1700
Data Index: 1341019 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1832. Min Act: -0.1700
Data Index: 1253654 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1832. Min Act: -0.1700
Data Index: 8337253 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1832. Min Act: -0.1700
Data Index: 6354974 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1832. Min Act: -0.1700
Data Index: 2505526 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1832. Min Act: -0.1700
Data Index: 2594363 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1520. Min Act: -0.1700
Data Index: 3793129 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1520. Min Act: -0.1700
Data Index: 4126687 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1520. Min Act: -0.1700
Data Index: 4188043 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2770. Min Range: -5.2770
Max Act: 5.1520. Min Act: -0.1700
Data Index: 6678617 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19