Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.9956. Min Act: -0.1700
Data Index: 3198399 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.9331. Min Act: -0.1700
Data Index: 5083669 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.9018. Min Act: -0.1700
Data Index: 1785369 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.9331. Min Act: -0.1700
Data Index: 8779406 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.9018. Min Act: -0.1700
Data Index: 5340586 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8706. Min Act: -0.1700
Data Index: 8536397 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8393. Min Act: -0.1700
Data Index: 2396691 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8706. Min Act: -0.1700
Data Index: 5764215 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8080. Min Act: -0.1700
Data Index: 5820724 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8080. Min Act: -0.1700
Data Index: 3296698 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8393. Min Act: -0.1700
Data Index: 3546974 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8080. Min Act: -0.1700
Data Index: 4587900 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.7768. Min Act: -0.1700
Data Index: 6152149 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8080. Min Act: -0.1700
Data Index: 1686797 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.7768. Min Act: -0.1700
Data Index: 4118798 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.7768. Min Act: -0.1700
Data Index: 3435752 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.7768. Min Act: -0.1700
Data Index: 2879156 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8080. Min Act: -0.1700
Data Index: 6045173 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.7455. Min Act: -0.1700
Data Index: 183411 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.7768. Min Act: -0.1700
Data Index: 2060283 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19