Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2450 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.3417. Min Act: -0.1700
Data Index: 7157296 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2946. Min Act: -0.1700
Data Index: 6820191 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2946. Min Act: -0.1700
Data Index: 3505217 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2789. Min Act: -0.1700
Data Index: 8631729 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2789. Min Act: -0.1700
Data Index: 5513463 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2789. Min Act: -0.1700
Data Index: 7276288 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2789. Min Act: -0.1700
Data Index: 1555353 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2632. Min Act: -0.1700
Data Index: 7642846 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2632. Min Act: -0.1700
Data Index: 2746209 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2632. Min Act: -0.1700
Data Index: 5741850 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2317. Min Act: -0.1700
Data Index: 168485 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2475. Min Act: -0.1700
Data Index: 4132815 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2475. Min Act: -0.1700
Data Index: 4561896 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2475. Min Act: -0.1700
Data Index: 5759027 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2475. Min Act: -0.1700
Data Index: 8653831 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2475. Min Act: -0.1700
Data Index: 1350722 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2475. Min Act: -0.1700
Data Index: 5584911 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2475. Min Act: -0.1700
Data Index: 2951544 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2317. Min Act: -0.1700
Data Index: 3259151 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3417. Min Range: -3.3417
Max Act: 3.2160. Min Act: -0.1700
Data Index: 2768965 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19