Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1830 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.8402. Min Act: -0.1700
Data Index: 2213363 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.8089. Min Act: -0.1700
Data Index: 8751350 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.7464. Min Act: -0.1700
Data Index: 5669810 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.6839. Min Act: -0.1700
Data Index: 8286773 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.6839. Min Act: -0.1700
Data Index: 8555739 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.6839. Min Act: -0.1700
Data Index: 5534728 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.6527. Min Act: -0.1700
Data Index: 6912793 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5902. Min Act: -0.1700
Data Index: 1300104 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5902. Min Act: -0.1700
Data Index: 8039502 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.6527. Min Act: -0.1700
Data Index: 63256 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5902. Min Act: -0.1700
Data Index: 3955175 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.6214. Min Act: -0.1700
Data Index: 992032 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5902. Min Act: -0.1700
Data Index: 6474611 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5902. Min Act: -0.1700
Data Index: 576553 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5589. Min Act: -0.1700
Data Index: 1906286 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5277. Min Act: -0.1700
Data Index: 3337103 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5277. Min Act: -0.1700
Data Index: 7756679 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.5277. Min Act: -0.1700
Data Index: 4652228 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.4964. Min Act: -0.1700
Data Index: 3682197 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8402. Min Range: -5.8402
Max Act: 5.4964. Min Act: -0.1700
Data Index: 2128254 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19