Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0457. Min Range: -8.0457
Max Act: 8.0457. Min Act: -0.1700
Data Index: 5046279 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0457. Min Range: -8.0457
Max Act: 8.0457. Min Act: -0.1700
Data Index: 4474557 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.9832. Min Act: -0.1700
Data Index: 1593802 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.8582. Min Act: -0.1700
Data Index: 4567235 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.8582. Min Act: -0.1700
Data Index: 4716987 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.8582. Min Act: -0.1700
Data Index: 302865 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.7957. Min Act: -0.1700
Data Index: 4383298 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.7957. Min Act: -0.1700
Data Index: 3315615 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.6707. Min Act: -0.1700
Data Index: 1366581 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.6707. Min Act: -0.1700
Data Index: 4942929 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.6707. Min Act: -0.1700
Data Index: 42413 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.6707. Min Act: -0.1700
Data Index: 3273214 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.6707. Min Act: -0.1700
Data Index: 2029662 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.6082. Min Act: -0.1700
Data Index: 8163890 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.5457. Min Act: -0.1700
Data Index: 8528706 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.5457. Min Act: -0.1700
Data Index: 5666597 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.5144. Min Act: -0.1700
Data Index: 6502041 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.4832. Min Act: -0.1700
Data Index: 269887 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.4832. Min Act: -0.1700
Data Index: 3531673 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0457. Min Range: -8.0457
Max Act: 7.4519. Min Act: -0.1700
Data Index: 6524146 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19