Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2681 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.9080. Min Act: -0.1700
Data Index: 3883854 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.9080. Min Act: -0.1700
Data Index: 3305446 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.8921. Min Act: -0.1700
Data Index: 6639656 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.8286. Min Act: -0.1700
Data Index: 4446640 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.8445. Min Act: -0.1700
Data Index: 2044378 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.8286. Min Act: -0.1700
Data Index: 3907661 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.8286. Min Act: -0.1700
Data Index: 1466848 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.8127. Min Act: -0.1700
Data Index: 2517660 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.7968. Min Act: -0.1700
Data Index: 8654496 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.7808. Min Act: -0.1700
Data Index: 1717985 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.7968. Min Act: -0.1700
Data Index: 1893961 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.7968. Min Act: -0.1700
Data Index: 7464545 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.7968. Min Act: -0.1700
Data Index: 7952323 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.7808. Min Act: -0.1700
Data Index: 6486726 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.7649. Min Act: -0.1700
Data Index: 489942 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.7649. Min Act: -0.1700
Data Index: 2568294 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.7808. Min Act: -0.1700
Data Index: 880082 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.7808. Min Act: -0.1700
Data Index: 3871439 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.7808. Min Act: -0.1700
Data Index: 5385720 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9080. Min Range: -2.9080
Max Act: 2.7808. Min Act: -0.1700
Data Index: 1939834 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19