Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1754 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.2170. Min Act: -0.1700
Data Index: 7638955 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1232. Min Act: -0.1700
Data Index: 5627932 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.0295. Min Act: -0.1700
Data Index: 2372874 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.9982. Min Act: -0.1700
Data Index: 7732375 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.9670. Min Act: -0.1700
Data Index: 5102474 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.9045. Min Act: -0.1700
Data Index: 622774 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7795. Min Act: -0.1700
Data Index: 8129343 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7482. Min Act: -0.1700
Data Index: 2761898 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7795. Min Act: -0.1700
Data Index: 689545 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7795. Min Act: -0.1700
Data Index: 8363283 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7482. Min Act: -0.1700
Data Index: 4672208 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7482. Min Act: -0.1700
Data Index: 2742804 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7482. Min Act: -0.1700
Data Index: 6486942 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7482. Min Act: -0.1700
Data Index: 8701646 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7170. Min Act: -0.1700
Data Index: 8560345 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7170. Min Act: -0.1700
Data Index: 1835892 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.6857. Min Act: -0.1700
Data Index: 8330253 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7170. Min Act: -0.1700
Data Index: 1503681 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.6857. Min Act: -0.1700
Data Index: 3074107 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.6545. Min Act: -0.1700
Data Index: 6124332 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19