Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 815 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0052. Min Range: -7.0052
Max Act: 7.0052. Min Act: -0.1700
Data Index: 4580307 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.8489. Min Act: -0.1700
Data Index: 5871293 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.8802. Min Act: -0.1700
Data Index: 817541 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.7864. Min Act: -0.1700
Data Index: 6650383 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.7864. Min Act: -0.1700
Data Index: 6212685 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.7552. Min Act: -0.1700
Data Index: 8536276 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.7864. Min Act: -0.1700
Data Index: 4411963 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.7239. Min Act: -0.1700
Data Index: 4895773 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.7239. Min Act: -0.1700
Data Index: 4347168 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.7239. Min Act: -0.1700
Data Index: 3084455 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.6614. Min Act: -0.1700
Data Index: 5650584 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.6927. Min Act: -0.1700
Data Index: 4842389 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.5989. Min Act: -0.1700
Data Index: 7050943 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.6302. Min Act: -0.1700
Data Index: 6019580 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.6302. Min Act: -0.1700
Data Index: 6920040 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.6302. Min Act: -0.1700
Data Index: 8740714 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.5989. Min Act: -0.1700
Data Index: 5761265 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.5989. Min Act: -0.1700
Data Index: 5980067 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.5989. Min Act: -0.1700
Data Index: 3324316 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0052. Min Range: -7.0052
Max Act: 6.5989. Min Act: -0.1700
Data Index: 4222704 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19