Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4445 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.5968. Min Act: -0.1700
Data Index: 1813796 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.5323. Min Act: -0.1700
Data Index: 6803288 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.4999. Min Act: -0.1700
Data Index: 3715469 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.4024. Min Act: -0.1700
Data Index: 3767738 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.3370. Min Act: -0.1700
Data Index: 1793643 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.3205. Min Act: -0.1700
Data Index: 1609686 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.3041. Min Act: -0.1700
Data Index: 170515 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.2877. Min Act: -0.1700
Data Index: 4470954 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.2877. Min Act: -0.1700
Data Index: 6366029 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.3041. Min Act: -0.1700
Data Index: 5517098 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.2877. Min Act: -0.1700
Data Index: 4024797 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.2877. Min Act: -0.1700
Data Index: 1023773 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.2877. Min Act: -0.1700
Data Index: 400859 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.2712. Min Act: -0.1700
Data Index: 2796623 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.2547. Min Act: -0.1700
Data Index: 5137582 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.2547. Min Act: -0.1700
Data Index: 6146026 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.2381. Min Act: -0.1700
Data Index: 3931745 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.2216. Min Act: -0.1700
Data Index: 7647355 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.2547. Min Act: -0.1700
Data Index: 3275652 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5968. Min Range: -2.5968
Max Act: 2.2216. Min Act: -0.1700
Data Index: 995251 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19