Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2943 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4172. Min Range: -7.4172
Max Act: 7.4172. Min Act: -0.1700
Data Index: 6389713 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4172. Min Range: -7.4172
Max Act: 7.3547. Min Act: -0.1700
Data Index: 742469 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4172. Min Range: -7.4172
Max Act: 7.0734. Min Act: -0.1700
Data Index: 7280292 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4172. Min Range: -7.4172
Max Act: 7.0734. Min Act: -0.1700
Data Index: 3480053 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4172. Min Range: -7.4172
Max Act: 7.0422. Min Act: -0.1700
Data Index: 5032650 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.9484. Min Act: -0.1700
Data Index: 4571777 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.9484. Min Act: -0.1700
Data Index: 8409116 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.9484. Min Act: -0.1700
Data Index: 768017 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.9172. Min Act: -0.1700
Data Index: 4505736 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.8859. Min Act: -0.1700
Data Index: 56431 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.8547. Min Act: -0.1700
Data Index: 6243986 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.8859. Min Act: -0.1700
Data Index: 5649795 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.8547. Min Act: -0.1700
Data Index: 8021625 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.8234. Min Act: -0.1700
Data Index: 894751 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.8234. Min Act: -0.1700
Data Index: 2801924 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.8234. Min Act: -0.1700
Data Index: 5023215 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.7922. Min Act: -0.1700
Data Index: 2780178 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.7922. Min Act: -0.1700
Data Index: 2336030 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.7609. Min Act: -0.1700
Data Index: 1669978 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4172. Min Range: -7.4172
Max Act: 6.7922. Min Act: -0.1700
Data Index: 2118957 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19