Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.3612. Min Act: -0.1700
Data Index: 6090976 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.3612. Min Act: -0.1700
Data Index: 2702101 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.2987. Min Act: -0.1700
Data Index: 8016832 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.2674. Min Act: -0.1700
Data Index: 8301870 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.2362. Min Act: -0.1700
Data Index: 5919750 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.2362. Min Act: -0.1700
Data Index: 394428 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.2362. Min Act: -0.1700
Data Index: 2438686 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.2362. Min Act: -0.1700
Data Index: 1116173 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.2049. Min Act: -0.1700
Data Index: 8765348 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.1424. Min Act: -0.1700
Data Index: 6832507 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.1112. Min Act: -0.1700
Data Index: 1210423 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.1112. Min Act: -0.1700
Data Index: 6919843 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.1112. Min Act: -0.1700
Data Index: 1379132 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.1112. Min Act: -0.1700
Data Index: 4221463 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.0799. Min Act: -0.1700
Data Index: 5118669 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.0799. Min Act: -0.1700
Data Index: 382332 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.0799. Min Act: -0.1700
Data Index: 6160968 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.0799. Min Act: -0.1700
Data Index: 2390671 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.0487. Min Act: -0.1700
Data Index: 1712157 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3612. Min Range: -5.3612
Max Act: 5.0487. Min Act: -0.1700
Data Index: 3134100 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19