Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5898 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.3382. Min Act: -0.1700
Data Index: 3590928 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.2757. Min Act: -0.1700
Data Index: 8125724 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.2757. Min Act: -0.1700
Data Index: 4471858 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.2757. Min Act: -0.1700
Data Index: 6144511 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.2444. Min Act: -0.1700
Data Index: 1295734 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.2444. Min Act: -0.1700
Data Index: 4249301 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.2132. Min Act: -0.1700
Data Index: 4493444 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.2444. Min Act: -0.1700
Data Index: 4450973 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.1819. Min Act: -0.1700
Data Index: 5837790 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.1819. Min Act: -0.1700
Data Index: 1534564 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.1819. Min Act: -0.1700
Data Index: 8685953 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.1507. Min Act: -0.1700
Data Index: 3459632 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.1507. Min Act: -0.1700
Data Index: 7500344 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.1507. Min Act: -0.1700
Data Index: 7029708 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.1507. Min Act: -0.1700
Data Index: 2695935 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.1507. Min Act: -0.1700
Data Index: 3411055 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.1819. Min Act: -0.1700
Data Index: 3624028 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.1194. Min Act: -0.1700
Data Index: 5268857 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.1194. Min Act: -0.1700
Data Index: 4670877 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3382. Min Range: -5.3382
Max Act: 5.1194. Min Act: -0.1700
Data Index: 6306471 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19