Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1312 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0233. Min Range: -3.0233
Max Act: 3.0233. Min Act: -0.1700
Data Index: 5561187 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.9601. Min Act: -0.1700
Data Index: 438217 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.9284. Min Act: -0.1700
Data Index: 247663 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.9126. Min Act: -0.1700
Data Index: 4910292 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8967. Min Act: -0.1700
Data Index: 2348746 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8967. Min Act: -0.1700
Data Index: 755135 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8967. Min Act: -0.1700
Data Index: 1298504 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8650. Min Act: -0.1700
Data Index: 140361 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8650. Min Act: -0.1700
Data Index: 2672644 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8650. Min Act: -0.1700
Data Index: 5627040 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8650. Min Act: -0.1700
Data Index: 7263128 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8650. Min Act: -0.1700
Data Index: 1406990 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8650. Min Act: -0.1700
Data Index: 5900094 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8650. Min Act: -0.1700
Data Index: 489990 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8491. Min Act: -0.1700
Data Index: 6583412 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8491. Min Act: -0.1700
Data Index: 4825183 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8491. Min Act: -0.1700
Data Index: 6735592 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8650. Min Act: -0.1700
Data Index: 2485312 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8491. Min Act: -0.1700
Data Index: 3827084 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0233. Min Range: -3.0233
Max Act: 2.8491. Min Act: -0.1700
Data Index: 3195398 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19