Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2268 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.8581. Min Act: -0.1700
Data Index: 4510435 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.4518. Min Act: -0.1700
Data Index: 2992192 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.3893. Min Act: -0.1700
Data Index: 5544872 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.3581. Min Act: -0.1700
Data Index: 5751324 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.2956. Min Act: -0.1700
Data Index: 3212901 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.3268. Min Act: -0.1700
Data Index: 4332420 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.3268. Min Act: -0.1700
Data Index: 3843004 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.2956. Min Act: -0.1700
Data Index: 4781606 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.2643. Min Act: -0.1700
Data Index: 5386 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.2643. Min Act: -0.1700
Data Index: 6836784 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.2331. Min Act: -0.1700
Data Index: 7781744 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.2331. Min Act: -0.1700
Data Index: 8648365 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.2331. Min Act: -0.1700
Data Index: 927314 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.2018. Min Act: -0.1700
Data Index: 7212233 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.2018. Min Act: -0.1700
Data Index: 7092282 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.2018. Min Act: -0.1700
Data Index: 3558056 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.2018. Min Act: -0.1700
Data Index: 3496861 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.2018. Min Act: -0.1700
Data Index: 1535940 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.2018. Min Act: -0.1700
Data Index: 6017506 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8581. Min Range: -5.8581
Max Act: 5.1706. Min Act: -0.1700
Data Index: 4456680 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19