Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 643 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.6049. Min Act: -0.1700
Data Index: 5639158 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.4799. Min Act: -0.1700
Data Index: 8554954 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.2924. Min Act: -0.1700
Data Index: 269107 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.1987. Min Act: -0.1700
Data Index: 5414307 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.2299. Min Act: -0.1700
Data Index: 7518771 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.1674. Min Act: -0.1700
Data Index: 5982148 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.1674. Min Act: -0.1700
Data Index: 3442006 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.1362. Min Act: -0.1700
Data Index: 3202051 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.1362. Min Act: -0.1700
Data Index: 1202819 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.1049. Min Act: -0.1700
Data Index: 6796533 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.1049. Min Act: -0.1700
Data Index: 8157194 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.0737. Min Act: -0.1700
Data Index: 4598150 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.0737. Min Act: -0.1700
Data Index: 7617769 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.0424. Min Act: -0.1700
Data Index: 4437770 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.0424. Min Act: -0.1700
Data Index: 8396612 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6049. Min Range: -5.6049
Max Act: 5.0112. Min Act: -0.1700
Data Index: 581650 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6049. Min Range: -5.6049
Max Act: 4.9799. Min Act: -0.1700
Data Index: 7165985 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6049. Min Range: -5.6049
Max Act: 4.9799. Min Act: -0.1700
Data Index: 2983774 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6049. Min Range: -5.6049
Max Act: 4.9799. Min Act: -0.1700
Data Index: 8421411 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6049. Min Range: -5.6049
Max Act: 4.9799. Min Act: -0.1700
Data Index: 6377046 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19