Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4318 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4038. Min Range: -9.4038
Max Act: 9.4038. Min Act: -0.1700
Data Index: 7110681 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4038. Min Range: -9.4038
Max Act: 9.4038. Min Act: -0.1700
Data Index: 6614541 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4038. Min Range: -9.4038
Max Act: 9.4038. Min Act: -0.1700
Data Index: 6179037 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4038. Min Range: -9.4038
Max Act: 9.3413. Min Act: -0.1700
Data Index: 4468713 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4038. Min Range: -9.4038
Max Act: 9.3413. Min Act: -0.1700
Data Index: 2520317 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4038. Min Range: -9.4038
Max Act: 9.2163. Min Act: -0.1700
Data Index: 5066489 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4038. Min Range: -9.4038
Max Act: 9.1538. Min Act: -0.1700
Data Index: 7392822 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4038. Min Range: -9.4038
Max Act: 9.1538. Min Act: -0.1700
Data Index: 2830347 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4038. Min Range: -9.4038
Max Act: 9.0913. Min Act: -0.1700
Data Index: 130801 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4038. Min Range: -9.4038
Max Act: 9.0913. Min Act: -0.1700
Data Index: 1660176 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4038. Min Range: -9.4038
Max Act: 8.9663. Min Act: -0.1700
Data Index: 5474025 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4038. Min Range: -9.4038
Max Act: 9.0288. Min Act: -0.1700
Data Index: 4846586 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4038. Min Range: -9.4038
Max Act: 8.9663. Min Act: -0.1700
Data Index: 8162376 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4038. Min Range: -9.4038
Max Act: 9.0288. Min Act: -0.1700
Data Index: 339345 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4038. Min Range: -9.4038
Max Act: 9.0288. Min Act: -0.1700
Data Index: 6814163 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4038. Min Range: -9.4038
Max Act: 8.9663. Min Act: -0.1700
Data Index: 6716263 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4038. Min Range: -9.4038
Max Act: 8.9038. Min Act: -0.1700
Data Index: 3972126 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4038. Min Range: -9.4038
Max Act: 8.9038. Min Act: -0.1700
Data Index: 2380515 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4038. Min Range: -9.4038
Max Act: 8.9038. Min Act: -0.1700
Data Index: 7732594 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4038. Min Range: -9.4038
Max Act: 8.8413. Min Act: -0.1700
Data Index: 3454277 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19