Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3817 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.2888. Min Act: -0.1700
Data Index: 3711798 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.3201. Min Act: -0.1700
Data Index: 5578631 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.1951. Min Act: -0.1700
Data Index: 2146287 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.1013. Min Act: -0.1700
Data Index: 3442478 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.0700. Min Act: -0.1700
Data Index: 8827644 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.0700. Min Act: -0.1700
Data Index: 4272101 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.0388. Min Act: -0.1700
Data Index: 4394359 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.0075. Min Act: -0.1700
Data Index: 1796517 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3201. Min Range: -4.3201
Max Act: 3.9450. Min Act: -0.1700
Data Index: 5462069 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3201. Min Range: -4.3201
Max Act: 3.9450. Min Act: -0.1700
Data Index: 4527314 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3201. Min Range: -4.3201
Max Act: 3.9450. Min Act: -0.1700
Data Index: 3783447 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3201. Min Range: -4.3201
Max Act: 3.9450. Min Act: -0.1700
Data Index: 7265795 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3201. Min Range: -4.3201
Max Act: 3.9450. Min Act: -0.1700
Data Index: 6528093 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3201. Min Range: -4.3201
Max Act: 3.9137. Min Act: -0.1700
Data Index: 7389546 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3201. Min Range: -4.3201
Max Act: 3.9137. Min Act: -0.1700
Data Index: 2453508 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3201. Min Range: -4.3201
Max Act: 3.9137. Min Act: -0.1700
Data Index: 4580062 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3201. Min Range: -4.3201
Max Act: 3.9137. Min Act: -0.1700
Data Index: 4484628 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3201. Min Range: -4.3201
Max Act: 3.9137. Min Act: -0.1700
Data Index: 448984 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3201. Min Range: -4.3201
Max Act: 3.8825. Min Act: -0.1700
Data Index: 6026128 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3201. Min Range: -4.3201
Max Act: 3.8825. Min Act: -0.1700
Data Index: 7343371 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19