Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5555 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.9950. Min Act: -0.1700
Data Index: 4286124 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.9950. Min Act: -0.1700
Data Index: 2760468 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.9950. Min Act: -0.1700
Data Index: 1613000 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.9325. Min Act: -0.1700
Data Index: 65417 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.7450. Min Act: -0.1700
Data Index: 4904758 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.4950. Min Act: -0.1700
Data Index: 6664343 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.5575. Min Act: -0.1700
Data Index: 4809584 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.4950. Min Act: -0.1700
Data Index: 7465259 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.4950. Min Act: -0.1700
Data Index: 3777335 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.4637. Min Act: -0.1700
Data Index: 7000114 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.4950. Min Act: -0.1700
Data Index: 712614 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.4325. Min Act: -0.1700
Data Index: 5382313 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.4325. Min Act: -0.1700
Data Index: 3843155 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.4012. Min Act: -0.1700
Data Index: 3124292 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.4012. Min Act: -0.1700
Data Index: 5462193 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.4012. Min Act: -0.1700
Data Index: 7805144 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.4325. Min Act: -0.1700
Data Index: 5284947 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.3700. Min Act: -0.1700
Data Index: 4970464 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.3700. Min Act: -0.1700
Data Index: 6115914 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9950. Min Range: -7.9950
Max Act: 7.3075. Min Act: -0.1700
Data Index: 5408953 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19