Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3444 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.8615. Min Act: -0.1700
Data Index: 5187312 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.8615. Min Act: -0.1700
Data Index: 8507408 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.7990. Min Act: -0.1700
Data Index: 4128475 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.7365. Min Act: -0.1700
Data Index: 272277 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.7365. Min Act: -0.1700
Data Index: 1797169 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6740. Min Act: -0.1700
Data Index: 6320625 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6740. Min Act: -0.1700
Data Index: 5896169 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6740. Min Act: -0.1700
Data Index: 5257187 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6740. Min Act: -0.1700
Data Index: 8419963 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6740. Min Act: -0.1700
Data Index: 4649106 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6740. Min Act: -0.1700
Data Index: 7489317 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6740. Min Act: -0.1700
Data Index: 1284828 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6740. Min Act: -0.1700
Data Index: 6739624 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6115. Min Act: -0.1700
Data Index: 434442 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6115. Min Act: -0.1700
Data Index: 3065364 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6115. Min Act: -0.1700
Data Index: 399581 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6115. Min Act: -0.1700
Data Index: 246334 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6115. Min Act: -0.1700
Data Index: 3355435 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6115. Min Act: -0.1700
Data Index: 1344984 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8615. Min Range: -6.8615
Max Act: 6.6115. Min Act: -0.1700
Data Index: 6272852 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19