Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1689 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.3900. Min Act: -0.1700
Data Index: 3136889 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.3586. Min Act: -0.1700
Data Index: 3954409 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.3586. Min Act: -0.1700
Data Index: 8679897 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.3272. Min Act: -0.1700
Data Index: 3954411 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.2958. Min Act: -0.1700
Data Index: 5343640 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.2644. Min Act: -0.1700
Data Index: 1695331 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.2330. Min Act: -0.1700
Data Index: 2159592 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.2487. Min Act: -0.1700
Data Index: 3757950 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.2330. Min Act: -0.1700
Data Index: 1911669 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.2173. Min Act: -0.1700
Data Index: 5094121 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.1858. Min Act: -0.1700
Data Index: 76980 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.1858. Min Act: -0.1700
Data Index: 6207615 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.1701. Min Act: -0.1700
Data Index: 3400495 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.1701. Min Act: -0.1700
Data Index: 1740626 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.1386. Min Act: -0.1700
Data Index: 6310007 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.1386. Min Act: -0.1700
Data Index: 665692 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.1386. Min Act: -0.1700
Data Index: 1596327 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.1386. Min Act: -0.1700
Data Index: 8358582 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.1386. Min Act: -0.1700
Data Index: 4390618 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3900. Min Range: -3.3900
Max Act: 3.1229. Min Act: -0.1700
Data Index: 5181955 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19