Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3059 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6593. Min Range: -2.6593
Max Act: 2.6593. Min Act: -0.1700
Data Index: 5983168 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6593. Min Range: -2.6593
Max Act: 2.5789. Min Act: -0.1700
Data Index: 8245158 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6593. Min Range: -2.6593
Max Act: 2.2693. Min Act: -0.1700
Data Index: 2330046 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.9515. Min Act: -0.1700
Data Index: 5551141 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.9345. Min Act: -0.1700
Data Index: 5983171 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.9004. Min Act: -0.1700
Data Index: 5551136 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.8663. Min Act: -0.1700
Data Index: 4030642 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.8492. Min Act: -0.1700
Data Index: 1862771 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.8320. Min Act: -0.1700
Data Index: 4125247 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.7976. Min Act: -0.1700
Data Index: 811584 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.7976. Min Act: -0.1650
Data Index: 5504823 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.7976. Min Act: -0.1700
Data Index: 1252964 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.7804. Min Act: -0.1700
Data Index: 5773669 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.7976. Min Act: -0.1700
Data Index: 7698118 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.7459. Min Act: -0.1699
Data Index: 1059753 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.7459. Min Act: -0.1700
Data Index: 5551139 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.7632. Min Act: -0.1700
Data Index: 2363294 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.7459. Min Act: -0.1700
Data Index: 2149361 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.7286. Min Act: -0.1700
Data Index: 2480973 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6593. Min Range: -2.6593
Max Act: 1.7113. Min Act: -0.1700
Data Index: 7119517 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19