Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.9235. Min Act: -0.1700
Data Index: 1881417 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.8610. Min Act: -0.1700
Data Index: 2387723 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.7985. Min Act: -0.1700
Data Index: 7252141 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.7672. Min Act: -0.1700
Data Index: 1644828 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.7672. Min Act: -0.1700
Data Index: 2784653 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.6735. Min Act: -0.1700
Data Index: 7718574 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.6422. Min Act: -0.1700
Data Index: 5843500 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.6735. Min Act: -0.1700
Data Index: 5761296 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.6422. Min Act: -0.1700
Data Index: 2044166 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.5172. Min Act: -0.1700
Data Index: 8282989 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.6422. Min Act: -0.1700
Data Index: 112724 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.5797. Min Act: -0.1700
Data Index: 3187430 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.4547. Min Act: -0.1700
Data Index: 7675310 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.5797. Min Act: -0.1700
Data Index: 1601118 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.5797. Min Act: -0.1700
Data Index: 7327153 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.5797. Min Act: -0.1700
Data Index: 171199 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.5485. Min Act: -0.1700
Data Index: 4917976 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.5485. Min Act: -0.1700
Data Index: 2869133 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.5485. Min Act: -0.1700
Data Index: 7711104 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9235. Min Range: -4.9235
Max Act: 4.4860. Min Act: -0.1700
Data Index: 5872805 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19