Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1393 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.4639. Min Act: -0.1700
Data Index: 6018333 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.3660. Min Act: -0.1700
Data Index: 7013430 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.3169. Min Act: -0.1700
Data Index: 8664501 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.3169. Min Act: -0.1700
Data Index: 8006870 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.3169. Min Act: -0.1700
Data Index: 6697151 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.3004. Min Act: -0.1700
Data Index: 4127487 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.3004. Min Act: -0.1700
Data Index: 3524048 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.2840. Min Act: -0.1700
Data Index: 4008838 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.2840. Min Act: -0.1700
Data Index: 4621196 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.2840. Min Act: -0.1700
Data Index: 5533525 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.2675. Min Act: -0.1700
Data Index: 1902117 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.2675. Min Act: -0.1700
Data Index: 5918154 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.2675. Min Act: -0.1700
Data Index: 5562353 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.2675. Min Act: -0.1700
Data Index: 2676372 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.2510. Min Act: -0.1700
Data Index: 7548697 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.2510. Min Act: -0.1700
Data Index: 614443 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.2510. Min Act: -0.1700
Data Index: 5787500 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.2510. Min Act: -0.1700
Data Index: 7430510 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.2510. Min Act: -0.1700
Data Index: 5185445 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4639. Min Range: -2.4639
Max Act: 2.2510. Min Act: -0.1700
Data Index: 6307045 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19