Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2396 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.4670. Min Act: -0.1700
Data Index: 7408943 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.2795. Min Act: -0.1700
Data Index: 6886036 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.3108. Min Act: -0.1700
Data Index: 8752839 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.2795. Min Act: -0.1700
Data Index: 3086497 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.2795. Min Act: -0.1700
Data Index: 7357844 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.2483. Min Act: -0.1700
Data Index: 1478429 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.2170. Min Act: -0.1700
Data Index: 2736287 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.2483. Min Act: -0.1700
Data Index: 8163747 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.2170. Min Act: -0.1700
Data Index: 1881677 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.2170. Min Act: -0.1700
Data Index: 167008 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.1858. Min Act: -0.1700
Data Index: 8155486 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.1858. Min Act: -0.1700
Data Index: 5336751 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.1858. Min Act: -0.1700
Data Index: 4825029 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.1858. Min Act: -0.1700
Data Index: 8211595 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.1545. Min Act: -0.1700
Data Index: 7669585 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.1545. Min Act: -0.1700
Data Index: 529361 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.1545. Min Act: -0.1700
Data Index: 7210222 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.1545. Min Act: -0.1700
Data Index: 7686862 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.1233. Min Act: -0.1700
Data Index: 7749612 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4670. Min Range: -5.4670
Max Act: 5.1545. Min Act: -0.1700
Data Index: 8115307 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19