Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0019. Min Range: -5.0019
Max Act: 5.0019. Min Act: -0.1700
Data Index: 2441678 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.8769. Min Act: -0.1700
Data Index: 6130545 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.8456. Min Act: -0.1700
Data Index: 4159831 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.8144. Min Act: -0.1700
Data Index: 7693124 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.7831. Min Act: -0.1700
Data Index: 7197695 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.7206. Min Act: -0.1700
Data Index: 8802778 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.7206. Min Act: -0.1700
Data Index: 5670834 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.7206. Min Act: -0.1700
Data Index: 8390407 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.6894. Min Act: -0.1700
Data Index: 1123603 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.6581. Min Act: -0.1700
Data Index: 6781982 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.6581. Min Act: -0.1700
Data Index: 5202306 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.6269. Min Act: -0.1700
Data Index: 2836363 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.6269. Min Act: -0.1700
Data Index: 5694150 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5956. Min Act: -0.1700
Data Index: 7445171 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5956. Min Act: -0.1700
Data Index: 573475 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5956. Min Act: -0.1700
Data Index: 1161886 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5956. Min Act: -0.1700
Data Index: 5341391 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5644. Min Act: -0.1700
Data Index: 7204238 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5644. Min Act: -0.1700
Data Index: 8133182 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5331. Min Act: -0.1700
Data Index: 4503230 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19