Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0982. Min Range: -3.0982
Max Act: 3.0982. Min Act: -0.1700
Data Index: 4456921 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0982. Min Range: -3.0982
Max Act: 3.0824. Min Act: -0.1700
Data Index: 6089075 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0982. Min Range: -3.0982
Max Act: 3.0667. Min Act: -0.1700
Data Index: 6675837 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0982. Min Range: -3.0982
Max Act: 3.0824. Min Act: -0.1700
Data Index: 1068856 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0982. Min Range: -3.0982
Max Act: 3.0351. Min Act: -0.1700
Data Index: 8322559 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0982. Min Range: -3.0982
Max Act: 3.0035. Min Act: -0.1700
Data Index: 2824015 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0982. Min Range: -3.0982
Max Act: 3.0193. Min Act: -0.1700
Data Index: 6318770 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0982. Min Range: -3.0982
Max Act: 3.0193. Min Act: -0.1700
Data Index: 7515398 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0982. Min Range: -3.0982
Max Act: 3.0351. Min Act: -0.1700
Data Index: 3167119 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0982. Min Range: -3.0982
Max Act: 3.0035. Min Act: -0.1700
Data Index: 5178937 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0982. Min Range: -3.0982
Max Act: 3.0035. Min Act: -0.1700
Data Index: 1965541 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0982. Min Range: -3.0982
Max Act: 2.9877. Min Act: -0.1700
Data Index: 169177 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0982. Min Range: -3.0982
Max Act: 2.9719. Min Act: -0.1700
Data Index: 7416252 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0982. Min Range: -3.0982
Max Act: 2.9086. Min Act: -0.1700
Data Index: 4262900 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0982. Min Range: -3.0982
Max Act: 2.8927. Min Act: -0.1700
Data Index: 1421606 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0982. Min Range: -3.0982
Max Act: 2.8927. Min Act: -0.1700
Data Index: 856162 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0982. Min Range: -3.0982
Max Act: 2.8927. Min Act: -0.1700
Data Index: 2708943 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0982. Min Range: -3.0982
Max Act: 2.8927. Min Act: -0.1700
Data Index: 5071804 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0982. Min Range: -3.0982
Max Act: 2.8927. Min Act: -0.1700
Data Index: 998139 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0982. Min Range: -3.0982
Max Act: 2.8768. Min Act: -0.1700
Data Index: 5560935 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19