Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2807 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.4982. Min Act: -0.1700
Data Index: 937380 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.3107. Min Act: -0.1700
Data Index: 5004764 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.2170. Min Act: -0.1700
Data Index: 1460094 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.2170. Min Act: -0.1700
Data Index: 8127756 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.1857. Min Act: -0.1700
Data Index: 6494709 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.1545. Min Act: -0.1700
Data Index: 6678296 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.1545. Min Act: -0.1700
Data Index: 1627145 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.1232. Min Act: -0.1700
Data Index: 925426 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.1232. Min Act: -0.1700
Data Index: 419922 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.1545. Min Act: -0.1700
Data Index: 858872 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.1232. Min Act: -0.1700
Data Index: 2913672 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.0920. Min Act: -0.1700
Data Index: 1493188 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.0920. Min Act: -0.1700
Data Index: 668353 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.0607. Min Act: -0.1700
Data Index: 3544330 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.0607. Min Act: -0.1700
Data Index: 2294723 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.0607. Min Act: -0.1700
Data Index: 302316 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.0295. Min Act: -0.1700
Data Index: 7748327 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.0607. Min Act: -0.1700
Data Index: 7911229 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4982. Min Range: -5.4982
Max Act: 5.0295. Min Act: -0.1700
Data Index: 8216198 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4982. Min Range: -5.4982
Max Act: 4.9982. Min Act: -0.1700
Data Index: 1015306 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19