Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4412 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.2334. Min Act: -0.1700
Data Index: 4868815 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.1709. Min Act: -0.1700
Data Index: 4175956 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.1709. Min Act: -0.1700
Data Index: 382692 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.1396. Min Act: -0.1700
Data Index: 5735985 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.1084. Min Act: -0.1700
Data Index: 5735989 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.1084. Min Act: -0.1700
Data Index: 1413137 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.1084. Min Act: -0.1700
Data Index: 2994542 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.0771. Min Act: -0.1700
Data Index: 4935343 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.0771. Min Act: -0.1700
Data Index: 6122585 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.0771. Min Act: -0.1700
Data Index: 4410779 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.0771. Min Act: -0.1699
Data Index: 5735986 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.0459. Min Act: -0.1700
Data Index: 4874925 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.0459. Min Act: -0.1700
Data Index: 3516263 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.0459. Min Act: -0.1700
Data Index: 5146583 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2334. Min Range: -5.2334
Max Act: 5.0146. Min Act: -0.1700
Data Index: 207076 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2334. Min Range: -5.2334
Max Act: 4.9834. Min Act: -0.1700
Data Index: 1062570 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2334. Min Range: -5.2334
Max Act: 4.9834. Min Act: -0.1700
Data Index: 32270 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2334. Min Range: -5.2334
Max Act: 4.9834. Min Act: -0.1700
Data Index: 502492 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2334. Min Range: -5.2334
Max Act: 4.9834. Min Act: -0.1700
Data Index: 2923150 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2334. Min Range: -5.2334
Max Act: 4.9834. Min Act: -0.1700
Data Index: 1016920 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19