Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5110 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3453. Min Range: -8.3453
Max Act: 8.3453. Min Act: -0.1700
Data Index: 8407292 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3453. Min Range: -8.3453
Max Act: 8.3453. Min Act: -0.1700
Data Index: 5013521 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3453. Min Range: -8.3453
Max Act: 8.0953. Min Act: -0.1700
Data Index: 4188865 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3453. Min Range: -8.3453
Max Act: 8.0640. Min Act: -0.1700
Data Index: 2324072 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3453. Min Range: -8.3453
Max Act: 8.0953. Min Act: -0.1700
Data Index: 7446299 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3453. Min Range: -8.3453
Max Act: 8.0328. Min Act: -0.1700
Data Index: 762163 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3453. Min Range: -8.3453
Max Act: 7.9390. Min Act: -0.1700
Data Index: 2578088 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3453. Min Range: -8.3453
Max Act: 7.9078. Min Act: -0.1700
Data Index: 4447320 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3453. Min Range: -8.3453
Max Act: 7.8765. Min Act: -0.1700
Data Index: 1988947 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3453. Min Range: -8.3453
Max Act: 7.8765. Min Act: -0.1700
Data Index: 1493957 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3453. Min Range: -8.3453
Max Act: 7.8765. Min Act: -0.1700
Data Index: 6677069 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3453. Min Range: -8.3453
Max Act: 7.8453. Min Act: -0.1700
Data Index: 5566897 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3453. Min Range: -8.3453
Max Act: 7.8140. Min Act: -0.1700
Data Index: 8140111 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3453. Min Range: -8.3453
Max Act: 7.7515. Min Act: -0.1700
Data Index: 8501436 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3453. Min Range: -8.3453
Max Act: 7.7515. Min Act: -0.1700
Data Index: 2505810 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3453. Min Range: -8.3453
Max Act: 7.7203. Min Act: -0.1700
Data Index: 879991 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3453. Min Range: -8.3453
Max Act: 7.7203. Min Act: -0.1700
Data Index: 4084770 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3453. Min Range: -8.3453
Max Act: 7.7203. Min Act: -0.1700
Data Index: 508203 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3453. Min Range: -8.3453
Max Act: 7.6890. Min Act: -0.1700
Data Index: 5501539 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3453. Min Range: -8.3453
Max Act: 7.6890. Min Act: -0.1700
Data Index: 3762620 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19