Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4451 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.6050. Min Act: -0.1700
Data Index: 4544064 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.5112. Min Act: -0.1700
Data Index: 4332726 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.4799. Min Act: -0.1700
Data Index: 313748 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.4799. Min Act: -0.1700
Data Index: 7639135 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.4174. Min Act: -0.1700
Data Index: 4929864 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.4174. Min Act: -0.1700
Data Index: 8030665 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.3862. Min Act: -0.1700
Data Index: 2325846 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.3549. Min Act: -0.1700
Data Index: 2749718 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.3237. Min Act: -0.1700
Data Index: 6022076 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.2924. Min Act: -0.1700
Data Index: 4321808 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.2924. Min Act: -0.1700
Data Index: 1541981 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.2612. Min Act: -0.1700
Data Index: 1116514 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.2612. Min Act: -0.1700
Data Index: 195471 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.2612. Min Act: -0.1700
Data Index: 5226888 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.1987. Min Act: -0.1700
Data Index: 5425595 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.2299. Min Act: -0.1700
Data Index: 4422217 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.2299. Min Act: -0.1700
Data Index: 7805613 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.2299. Min Act: -0.1700
Data Index: 7458421 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.2299. Min Act: -0.1700
Data Index: 3597019 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6050. Min Range: -4.6050
Max Act: 4.2299. Min Act: -0.1700
Data Index: 6802954 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19