Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.5689. Min Act: -0.1700
Data Index: 1369345 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.5376. Min Act: -0.1700
Data Index: 1696181 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.5376. Min Act: -0.1700
Data Index: 4810588 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.5376. Min Act: -0.1700
Data Index: 544071 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4749. Min Act: -0.1700
Data Index: 1761782 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4906. Min Act: -0.1700
Data Index: 103789 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4906. Min Act: -0.1700
Data Index: 2494229 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4749. Min Act: -0.1700
Data Index: 1610118 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4749. Min Act: -0.1700
Data Index: 3954623 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4749. Min Act: -0.1700
Data Index: 3215066 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4906. Min Act: -0.1700
Data Index: 2675696 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4593. Min Act: -0.1700
Data Index: 6453539 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4593. Min Act: -0.1700
Data Index: 8008749 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4436. Min Act: -0.1700
Data Index: 2108223 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4436. Min Act: -0.1700
Data Index: 6147856 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4749. Min Act: -0.1700
Data Index: 5495279 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4279. Min Act: -0.1700
Data Index: 319222 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4123. Min Act: -0.1700
Data Index: 5603473 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4279. Min Act: -0.1700
Data Index: 3792828 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4279. Min Act: -0.1700
Data Index: 3588731 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19