Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1331 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0761. Min Range: -6.0761
Max Act: 6.0761. Min Act: -0.1700
Data Index: 8771327 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.6386. Min Act: -0.1700
Data Index: 4834940 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.4511. Min Act: -0.1700
Data Index: 4113662 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.3886. Min Act: -0.1700
Data Index: 3465154 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.3574. Min Act: -0.1700
Data Index: 6112042 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.2949. Min Act: -0.1700
Data Index: 2905501 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.1699. Min Act: -0.1700
Data Index: 1180301 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.1699. Min Act: -0.1700
Data Index: 4411766 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.1699. Min Act: -0.1700
Data Index: 5252889 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.1386. Min Act: -0.1700
Data Index: 1073470 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.2011. Min Act: -0.1700
Data Index: 3946227 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.1386. Min Act: -0.1700
Data Index: 2609655 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.1699. Min Act: -0.1700
Data Index: 5813434 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.1699. Min Act: -0.1700
Data Index: 2025218 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.1386. Min Act: -0.1700
Data Index: 8729114 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.1386. Min Act: -0.1700
Data Index: 429006 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.1074. Min Act: -0.1700
Data Index: 2714701 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.1074. Min Act: -0.1700
Data Index: 3460186 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.0761. Min Act: -0.1700
Data Index: 6451637 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0761. Min Range: -6.0761
Max Act: 5.0761. Min Act: -0.1700
Data Index: 8120776 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19