Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1952 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.8134. Min Act: -0.1700
Data Index: 3231089 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.8134. Min Act: -0.1700
Data Index: 3397458 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.7665. Min Act: -0.1700
Data Index: 949219 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.7353. Min Act: -0.1700
Data Index: 2669438 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.6727. Min Act: -0.1700
Data Index: 6959026 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.6727. Min Act: -0.1700
Data Index: 111199 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.6727. Min Act: -0.1700
Data Index: 455856 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.6414. Min Act: -0.1700
Data Index: 3076258 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.6257. Min Act: -0.1700
Data Index: 1516087 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.6570. Min Act: -0.1700
Data Index: 2976469 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.6257. Min Act: -0.1700
Data Index: 3054352 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.6414. Min Act: -0.1700
Data Index: 6189183 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.6257. Min Act: -0.1700
Data Index: 1903943 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.6101. Min Act: -0.1700
Data Index: 7279102 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.5944. Min Act: -0.1700
Data Index: 197583 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.6257. Min Act: -0.1700
Data Index: 7333579 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.5788. Min Act: -0.1700
Data Index: 5504876 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.6101. Min Act: -0.1700
Data Index: 6294478 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.5631. Min Act: -0.1700
Data Index: 3736193 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8134. Min Range: -3.8134
Max Act: 3.5788. Min Act: -0.1700
Data Index: 4955011 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19