Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2353 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.5206. Min Act: -0.1700
Data Index: 7171310 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.4894. Min Act: -0.1700
Data Index: 717584 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.4269. Min Act: -0.1700
Data Index: 3407268 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.4269. Min Act: -0.1700
Data Index: 6807218 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.3644. Min Act: -0.1700
Data Index: 12296 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.4269. Min Act: -0.1700
Data Index: 3627190 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.3956. Min Act: -0.1700
Data Index: 1272931 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.3019. Min Act: -0.1700
Data Index: 7425606 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.3644. Min Act: -0.1700
Data Index: 3592909 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.3644. Min Act: -0.1700
Data Index: 2246168 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.3644. Min Act: -0.1700
Data Index: 7533647 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.3331. Min Act: -0.1700
Data Index: 4421518 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.3331. Min Act: -0.1700
Data Index: 6863469 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.3019. Min Act: -0.1700
Data Index: 2058224 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.3331. Min Act: -0.1700
Data Index: 3362706 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.3019. Min Act: -0.1700
Data Index: 3013065 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.3019. Min Act: -0.1700
Data Index: 3104945 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.2706. Min Act: -0.1700
Data Index: 4493710 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.3019. Min Act: -0.1700
Data Index: 7145758 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5206. Min Range: -4.5206
Max Act: 4.2706. Min Act: -0.1700
Data Index: 8176732 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19