Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2654. Min Range: -6.2654
Max Act: 6.2654. Min Act: -0.1700
Data Index: 3514741 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2654. Min Range: -6.2654
Max Act: 6.1092. Min Act: -0.1700
Data Index: 5623844 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2654. Min Range: -6.2654
Max Act: 6.0467. Min Act: -0.1700
Data Index: 2436291 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.8592. Min Act: -0.1700
Data Index: 6774524 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.8592. Min Act: -0.1700
Data Index: 3396261 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.8592. Min Act: -0.1700
Data Index: 1041133 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.8279. Min Act: -0.1700
Data Index: 7355581 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.7967. Min Act: -0.1700
Data Index: 3742236 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.7967. Min Act: -0.1700
Data Index: 6528311 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.7967. Min Act: -0.1700
Data Index: 8391721 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.7967. Min Act: -0.1700
Data Index: 1574848 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.8279. Min Act: -0.1700
Data Index: 3456973 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.7967. Min Act: -0.1700
Data Index: 3494096 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.7654. Min Act: -0.1700
Data Index: 5466313 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.7654. Min Act: -0.1700
Data Index: 5161274 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.7654. Min Act: -0.1700
Data Index: 7063297 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.7654. Min Act: -0.1700
Data Index: 5122003 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.7342. Min Act: -0.1700
Data Index: 999573 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.7967. Min Act: -0.1700
Data Index: 6910293 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2654. Min Range: -6.2654
Max Act: 5.7654. Min Act: -0.1700
Data Index: 4090222 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19