Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3361 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4042. Min Range: -6.4042
Max Act: 6.4042. Min Act: -0.1700
Data Index: 3521057 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4042. Min Range: -6.4042
Max Act: 6.2167. Min Act: -0.1700
Data Index: 8742793 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4042. Min Range: -6.4042
Max Act: 6.1542. Min Act: -0.1700
Data Index: 6996878 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4042. Min Range: -6.4042
Max Act: 6.1542. Min Act: -0.1700
Data Index: 954145 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4042. Min Range: -6.4042
Max Act: 6.0917. Min Act: -0.1700
Data Index: 4840873 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4042. Min Range: -6.4042
Max Act: 6.0917. Min Act: -0.1700
Data Index: 3815572 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4042. Min Range: -6.4042
Max Act: 6.0604. Min Act: -0.1700
Data Index: 8641152 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4042. Min Range: -6.4042
Max Act: 5.9979. Min Act: -0.1700
Data Index: 2378900 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4042. Min Range: -6.4042
Max Act: 6.0292. Min Act: -0.1700
Data Index: 6565912 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4042. Min Range: -6.4042
Max Act: 6.0292. Min Act: -0.1700
Data Index: 6315150 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4042. Min Range: -6.4042
Max Act: 6.0292. Min Act: -0.1700
Data Index: 4270086 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4042. Min Range: -6.4042
Max Act: 6.0292. Min Act: -0.1700
Data Index: 7342053 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4042. Min Range: -6.4042
Max Act: 6.0604. Min Act: -0.1700
Data Index: 7330797 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4042. Min Range: -6.4042
Max Act: 5.9979. Min Act: -0.1700
Data Index: 705688 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4042. Min Range: -6.4042
Max Act: 5.9667. Min Act: -0.1700
Data Index: 2937020 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4042. Min Range: -6.4042
Max Act: 5.9667. Min Act: -0.1700
Data Index: 3162368 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4042. Min Range: -6.4042
Max Act: 5.9354. Min Act: -0.1700
Data Index: 2765802 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4042. Min Range: -6.4042
Max Act: 5.9354. Min Act: -0.1700
Data Index: 4583168 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4042. Min Range: -6.4042
Max Act: 5.9354. Min Act: -0.1700
Data Index: 3496569 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4042. Min Range: -6.4042
Max Act: 5.9354. Min Act: -0.1700
Data Index: 7256016 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19