Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4826 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2609. Min Range: -7.2609
Max Act: 7.2609. Min Act: -0.1700
Data Index: 2304963 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2609. Min Range: -7.2609
Max Act: 7.0109. Min Act: -0.1700
Data Index: 3719988 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.8859. Min Act: -0.1700
Data Index: 6544573 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.8547. Min Act: -0.1700
Data Index: 5001507 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.6984. Min Act: -0.1700
Data Index: 4771256 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.6359. Min Act: -0.1700
Data Index: 2411405 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.6672. Min Act: -0.1700
Data Index: 4334223 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.5422. Min Act: -0.1700
Data Index: 3109261 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.5109. Min Act: -0.1700
Data Index: 1449178 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.5422. Min Act: -0.1700
Data Index: 6865973 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.5109. Min Act: -0.1700
Data Index: 2973660 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.4484. Min Act: -0.1700
Data Index: 6646198 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.4484. Min Act: -0.1700
Data Index: 5715980 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.4172. Min Act: -0.1700
Data Index: 5430362 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.3859. Min Act: -0.1700
Data Index: 4085573 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.3859. Min Act: -0.1700
Data Index: 8459667 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.3547. Min Act: -0.1700
Data Index: 2626476 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.3234. Min Act: -0.1700
Data Index: 3231543 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.2922. Min Act: -0.1700
Data Index: 3354181 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2609. Min Range: -7.2609
Max Act: 6.3234. Min Act: -0.1700
Data Index: 5902039 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19