Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4848 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.7276. Min Act: -0.1700
Data Index: 1408595 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.6963. Min Act: -0.1700
Data Index: 2328739 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.6651. Min Act: -0.1700
Data Index: 2545263 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.6651. Min Act: -0.1700
Data Index: 6258476 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.6338. Min Act: -0.1700
Data Index: 4198089 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.6026. Min Act: -0.1700
Data Index: 5425947 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.6026. Min Act: -0.1700
Data Index: 5795296 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5713. Min Act: -0.1699
Data Index: 4569670 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5713. Min Act: -0.1700
Data Index: 5425945 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5713. Min Act: -0.1700
Data Index: 7806235 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5713. Min Act: -0.1700
Data Index: 8588677 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5401. Min Act: -0.1700
Data Index: 6758006 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5401. Min Act: -0.1700
Data Index: 3213872 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5401. Min Act: -0.1700
Data Index: 6510499 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5401. Min Act: -0.1700
Data Index: 3518328 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5088. Min Act: -0.1700
Data Index: 6126259 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5088. Min Act: -0.1700
Data Index: 4464858 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5088. Min Act: -0.1700
Data Index: 5957395 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.5088. Min Act: -0.1700
Data Index: 6727093 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7276. Min Range: -5.7276
Max Act: 5.4776. Min Act: -0.1700
Data Index: 5216207 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19