Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3628 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0583. Min Range: -5.0583
Max Act: 5.0583. Min Act: -0.1699
Data Index: 2632428 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.9958. Min Act: -0.1700
Data Index: 3670872 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.9333. Min Act: -0.1698
Data Index: 820666 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.9645. Min Act: -0.1700
Data Index: 5615552 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.9333. Min Act: -0.1700
Data Index: 8391281 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.9333. Min Act: -0.1700
Data Index: 6626804 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.9333. Min Act: -0.1700
Data Index: 7749718 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.9020. Min Act: -0.1700
Data Index: 6914824 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.9020. Min Act: -0.1700
Data Index: 2157419 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.9020. Min Act: -0.1700
Data Index: 2764669 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.8708. Min Act: -0.1700
Data Index: 5507517 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.8083. Min Act: -0.1623
Data Index: 6601982 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.8708. Min Act: -0.1700
Data Index: 565902 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.8395. Min Act: -0.1700
Data Index: 5779173 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.8083. Min Act: -0.1700
Data Index: 4929885 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.8083. Min Act: -0.1700
Data Index: 931965 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.8083. Min Act: -0.1700
Data Index: 2333219 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.8083. Min Act: -0.1700
Data Index: 2178372 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.8083. Min Act: -0.1700
Data Index: 735134 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0583. Min Range: -5.0583
Max Act: 4.8083. Min Act: -0.1700
Data Index: 7369105 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19