Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4150 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3998. Min Range: -5.3998
Max Act: 5.3998. Min Act: -0.1700
Data Index: 6274462 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3998. Min Range: -5.3998
Max Act: 5.2748. Min Act: -0.1700
Data Index: 1262278 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3998. Min Range: -5.3998
Max Act: 5.2435. Min Act: -0.1700
Data Index: 751783 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3998. Min Range: -5.3998
Max Act: 5.1498. Min Act: -0.1700
Data Index: 751787 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3998. Min Range: -5.3998
Max Act: 5.0873. Min Act: -0.1700
Data Index: 3116299 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3998. Min Range: -5.3998
Max Act: 5.0560. Min Act: -0.1700
Data Index: 841676 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3998. Min Range: -5.3998
Max Act: 5.0873. Min Act: -0.1700
Data Index: 755520 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3998. Min Range: -5.3998
Max Act: 5.0248. Min Act: -0.1700
Data Index: 7614185 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3998. Min Range: -5.3998
Max Act: 5.0248. Min Act: -0.1700
Data Index: 6274461 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3998. Min Range: -5.3998
Max Act: 4.9935. Min Act: -0.1700
Data Index: 5954417 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3998. Min Range: -5.3998
Max Act: 5.0248. Min Act: -0.1700
Data Index: 26074 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3998. Min Range: -5.3998
Max Act: 4.9935. Min Act: -0.1700
Data Index: 107199 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3998. Min Range: -5.3998
Max Act: 4.9935. Min Act: -0.1700
Data Index: 696355 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3998. Min Range: -5.3998
Max Act: 4.9623. Min Act: -0.1700
Data Index: 5954418 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3998. Min Range: -5.3998
Max Act: 4.9623. Min Act: -0.1700
Data Index: 751784 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3998. Min Range: -5.3998
Max Act: 4.9623. Min Act: -0.1700
Data Index: 6274465 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3998. Min Range: -5.3998
Max Act: 4.9935. Min Act: -0.1700
Data Index: 841675 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3998. Min Range: -5.3998
Max Act: 4.9310. Min Act: -0.1700
Data Index: 2360133 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3998. Min Range: -5.3998
Max Act: 4.8998. Min Act: -0.1700
Data Index: 895240 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3998. Min Range: -5.3998
Max Act: 4.8998. Min Act: -0.1700
Data Index: 6274464 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19