Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4193 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0507. Min Range: -5.0507
Max Act: 5.0507. Min Act: -0.1700
Data Index: 4875249 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.9257. Min Act: -0.1700
Data Index: 6208104 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.9257. Min Act: -0.1700
Data Index: 5848203 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8945. Min Act: -0.1700
Data Index: 7169312 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8945. Min Act: -0.1700
Data Index: 4588293 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8320. Min Act: -0.1700
Data Index: 6208103 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8632. Min Act: -0.1700
Data Index: 6542934 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8320. Min Act: -0.1700
Data Index: 4282082 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8320. Min Act: -0.1700
Data Index: 5415782 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8320. Min Act: -0.1700
Data Index: 6802752 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8007. Min Act: -0.1697
Data Index: 58581 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8320. Min Act: -0.1700
Data Index: 5905527 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8007. Min Act: -0.1700
Data Index: 6010334 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8007. Min Act: -0.1700
Data Index: 6314156 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8007. Min Act: -0.1700
Data Index: 2945856 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.7695. Min Act: -0.1700
Data Index: 3272767 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8007. Min Act: -0.1700
Data Index: 4877981 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8007. Min Act: -0.1697
Data Index: 1508380 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8007. Min Act: -0.1700
Data Index: 5203892 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0507. Min Range: -5.0507
Max Act: 4.8007. Min Act: -0.1700
Data Index: 6139233 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19