Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2025 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.9586. Min Act: -0.1700
Data Index: 2453426 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.9428. Min Act: -0.1700
Data Index: 1961083 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8953. Min Act: -0.1700
Data Index: 623444 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8953. Min Act: -0.1700
Data Index: 4138460 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8794. Min Act: -0.1700
Data Index: 928770 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8635. Min Act: -0.1700
Data Index: 667834 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8477. Min Act: -0.1700
Data Index: 7345673 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8158. Min Act: -0.1700
Data Index: 637258 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8158. Min Act: -0.1700
Data Index: 3148869 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8318. Min Act: -0.1700
Data Index: 2230041 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8158. Min Act: -0.1700
Data Index: 4830035 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8158. Min Act: -0.1700
Data Index: 2247584 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8318. Min Act: -0.1700
Data Index: 7331287 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8158. Min Act: -0.1700
Data Index: 1308270 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8158. Min Act: -0.1700
Data Index: 6451739 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8158. Min Act: -0.1700
Data Index: 2956804 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8158. Min Act: -0.1700
Data Index: 692447 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8158. Min Act: -0.1700
Data Index: 3942560 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.8158. Min Act: -0.1700
Data Index: 7802082 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9586. Min Range: -2.9586
Max Act: 2.7999. Min Act: -0.1700
Data Index: 3306362 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19