Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1926 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0623. Min Range: -7.0623
Max Act: 7.0623. Min Act: -0.1700
Data Index: 8498414 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0623. Min Range: -7.0623
Max Act: 7.0310. Min Act: -0.1700
Data Index: 4189831 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.9685. Min Act: -0.1700
Data Index: 8104558 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.9685. Min Act: -0.1700
Data Index: 2073518 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.9060. Min Act: -0.1700
Data Index: 6871274 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.8435. Min Act: -0.1700
Data Index: 2633781 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.8123. Min Act: -0.1700
Data Index: 1312518 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.8123. Min Act: -0.1700
Data Index: 4447005 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.7810. Min Act: -0.1700
Data Index: 3340444 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.7810. Min Act: -0.1700
Data Index: 5795026 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.7810. Min Act: -0.1700
Data Index: 7884234 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.7810. Min Act: -0.1700
Data Index: 4222790 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.7185. Min Act: -0.1700
Data Index: 892713 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.7185. Min Act: -0.1700
Data Index: 6371045 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.7185. Min Act: -0.1700
Data Index: 2555542 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.6560. Min Act: -0.1700
Data Index: 8270871 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.6560. Min Act: -0.1700
Data Index: 8102177 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.6248. Min Act: -0.1700
Data Index: 5873557 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.6248. Min Act: -0.1700
Data Index: 7160048 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0623. Min Range: -7.0623
Max Act: 6.6248. Min Act: -0.1700
Data Index: 3329702 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19