Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.2293. Min Range: -10.2293
Max Act: 10.2293. Min Act: -0.1700
Data Index: 5227614 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2293. Min Range: -10.2293
Max Act: 9.2293. Min Act: -0.1700
Data Index: 2231786 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2293. Min Range: -10.2293
Max Act: 9.2293. Min Act: -0.1700
Data Index: 7797866 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2293. Min Range: -10.2293
Max Act: 9.1668. Min Act: -0.1700
Data Index: 6850192 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2293. Min Range: -10.2293
Max Act: 9.1043. Min Act: -0.1700
Data Index: 2287011 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2293. Min Range: -10.2293
Max Act: 9.0418. Min Act: -0.1700
Data Index: 3438081 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2293. Min Range: -10.2293
Max Act: 9.1043. Min Act: -0.1700
Data Index: 4736220 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2293. Min Range: -10.2293
Max Act: 9.0418. Min Act: -0.1700
Data Index: 3422778 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2293. Min Range: -10.2293
Max Act: 9.0418. Min Act: -0.1700
Data Index: 6897368 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2293. Min Range: -10.2293
Max Act: 9.0418. Min Act: -0.1700
Data Index: 2651706 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2293. Min Range: -10.2293
Max Act: 8.9793. Min Act: -0.1700
Data Index: 7200198 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2293. Min Range: -10.2293
Max Act: 8.8543. Min Act: -0.1700
Data Index: 3490836 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2293. Min Range: -10.2293
Max Act: 8.9168. Min Act: -0.1700
Data Index: 8769397 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2293. Min Range: -10.2293
Max Act: 8.9168. Min Act: -0.1700
Data Index: 4595170 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2293. Min Range: -10.2293
Max Act: 8.9168. Min Act: -0.1700
Data Index: 6257855 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2293. Min Range: -10.2293
Max Act: 8.9168. Min Act: -0.1700
Data Index: 3422777 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2293. Min Range: -10.2293
Max Act: 8.9168. Min Act: -0.1700
Data Index: 3438085 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2293. Min Range: -10.2293
Max Act: 8.9168. Min Act: -0.1700
Data Index: 3438075 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2293. Min Range: -10.2293
Max Act: 8.9168. Min Act: -0.1700
Data Index: 8588622 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2293. Min Range: -10.2293
Max Act: 8.8543. Min Act: -0.1700
Data Index: 6866429 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19