Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3128 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.5647. Min Act: -0.1700
Data Index: 2569396 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.3147. Min Act: -0.1700
Data Index: 5387643 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.2834. Min Act: -0.1700
Data Index: 2380220 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.2209. Min Act: -0.1700
Data Index: 1164131 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.2209. Min Act: -0.1700
Data Index: 531171 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.2209. Min Act: -0.1700
Data Index: 5304673 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.2209. Min Act: -0.1700
Data Index: 1701046 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.2209. Min Act: -0.1700
Data Index: 8712527 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.1897. Min Act: -0.1700
Data Index: 5304672 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.2209. Min Act: -0.1700
Data Index: 451111 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.1897. Min Act: -0.1700
Data Index: 1815236 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.1897. Min Act: -0.1700
Data Index: 6458497 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.1897. Min Act: -0.1700
Data Index: 3569927 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.1584. Min Act: -0.1699
Data Index: 5086638 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.1584. Min Act: -0.1700
Data Index: 5505894 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.1584. Min Act: -0.1700
Data Index: 7548634 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.1584. Min Act: -0.1700
Data Index: 4079217 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.1584. Min Act: -0.1700
Data Index: 3622569 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.1271. Min Act: -0.1700
Data Index: 5095 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5647. Min Range: -4.5647
Max Act: 4.1584. Min Act: -0.1700
Data Index: 4159724 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19