Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5425 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.6522. Min Act: -0.1700
Data Index: 2190294 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.6040. Min Act: -0.1697
Data Index: 2288085 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.4747. Min Act: -0.1700
Data Index: 3433202 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.4747. Min Act: -0.1666
Data Index: 2012359 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.4097. Min Act: -0.1700
Data Index: 6661269 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.4097. Min Act: -0.1698
Data Index: 3431967 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.4097. Min Act: -0.1640
Data Index: 2359994 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.3770. Min Act: -0.1700
Data Index: 7385993 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.3770. Min Act: -0.1699
Data Index: 8155401 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.3770. Min Act: -0.1686
Data Index: 4918839 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.3606. Min Act: -0.1545
Data Index: 8251029 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.3443. Min Act: -0.1658
Data Index: 5474115 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.3443. Min Act: -0.1696
Data Index: 4396077 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.3443. Min Act: -0.1666
Data Index: 3139571 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.3279. Min Act: -0.1699
Data Index: 1826987 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.2950. Min Act: -0.1700
Data Index: 613360 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.2950. Min Act: -0.1700
Data Index: 8241310 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.2785. Min Act: -0.1695
Data Index: 4824560 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.2785. Min Act: -0.1700
Data Index: 225191 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6522. Min Range: -2.6522
Max Act: 2.2785. Min Act: -0.1668
Data Index: 6358647 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19