Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2673 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0622. Min Range: -6.0622
Max Act: 6.0622. Min Act: -0.1700
Data Index: 659187 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.9997. Min Act: -0.1700
Data Index: 2621750 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0622. Min Range: -6.0622
Max Act: 6.0310. Min Act: -0.1700
Data Index: 6372933 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.9685. Min Act: -0.1700
Data Index: 1222224 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.8747. Min Act: -0.1700
Data Index: 4548434 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.7497. Min Act: -0.1700
Data Index: 7438500 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.6872. Min Act: -0.1700
Data Index: 4476091 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.6872. Min Act: -0.1700
Data Index: 567107 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.7185. Min Act: -0.1700
Data Index: 5532317 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.6872. Min Act: -0.1700
Data Index: 8441500 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.6872. Min Act: -0.1700
Data Index: 7582424 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.6247. Min Act: -0.1700
Data Index: 3509725 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.6560. Min Act: -0.1700
Data Index: 5628108 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.6247. Min Act: -0.1700
Data Index: 7709304 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.6560. Min Act: -0.1700
Data Index: 2127172 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.6560. Min Act: -0.1700
Data Index: 6376292 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.6560. Min Act: -0.1700
Data Index: 1997474 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.6247. Min Act: -0.1700
Data Index: 8615725 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.6560. Min Act: -0.1700
Data Index: 2932025 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0622. Min Range: -6.0622
Max Act: 5.6560. Min Act: -0.1700
Data Index: 7487951 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19