Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2641 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.6216. Min Act: -0.1699
Data Index: 5911136 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.5282. Min Act: -0.1684
Data Index: 3813260 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.5358. Min Act: -0.1700
Data Index: 3714959 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.5206. Min Act: -0.1700
Data Index: 6523244 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.5206. Min Act: -0.1690
Data Index: 7951583 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.5130. Min Act: -0.1657
Data Index: 8388025 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.4904. Min Act: -0.1694
Data Index: 4639481 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.4904. Min Act: -0.1700
Data Index: 2136141 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.4904. Min Act: -0.1687
Data Index: 5968304 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.4979. Min Act: -0.1688
Data Index: 7123758 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.4904. Min Act: -0.1596
Data Index: 2237415 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.4756. Min Act: -0.1697
Data Index: 5906091 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.4756. Min Act: -0.1689
Data Index: 5906096 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.4756. Min Act: -0.1699
Data Index: 688722 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.4756. Min Act: -0.1700
Data Index: 688723 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.4756. Min Act: -0.1614
Data Index: 5906093 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.4756. Min Act: -0.1577
Data Index: 5906088 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.4756. Min Act: -0.1694
Data Index: 688725 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.4756. Min Act: -0.1697
Data Index: 428653 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6216. Min Range: -0.6216
Max Act: 0.4682. Min Act: -0.1698
Data Index: 277457 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19