Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2508 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.7048. Min Act: -0.1700
Data Index: 4039728 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.6423. Min Act: -0.1700
Data Index: 2028622 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.6110. Min Act: -0.1700
Data Index: 6972462 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.6110. Min Act: -0.1700
Data Index: 2191316 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.6110. Min Act: -0.1700
Data Index: 284688 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.5485. Min Act: -0.1700
Data Index: 3380499 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.5485. Min Act: -0.1700
Data Index: 2367669 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.5485. Min Act: -0.1700
Data Index: 6972463 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.5485. Min Act: -0.1700
Data Index: 1027537 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.5173. Min Act: -0.1700
Data Index: 7124413 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4548. Min Act: -0.1700
Data Index: 457457 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4548. Min Act: -0.1700
Data Index: 7825536 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4548. Min Act: -0.1700
Data Index: 3341156 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4548. Min Act: -0.1700
Data Index: 3581234 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4548. Min Act: -0.1700
Data Index: 3380500 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4235. Min Act: -0.1700
Data Index: 4808101 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.3610. Min Act: -0.1700
Data Index: 3291262 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4235. Min Act: -0.1700
Data Index: 2746126 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.3923. Min Act: -0.1700
Data Index: 2746127 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4235. Min Act: -0.1700
Data Index: 543182 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19