Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1116 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9973. Min Act: -0.1700
Data Index: 6648855 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0146. Min Range: -1.0146
Max Act: 1.0146. Min Act: -0.1700
Data Index: 5281771 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9799. Min Act: -0.1700
Data Index: 4598935 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9626. Min Act: -0.1700
Data Index: 4408210 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9454. Min Act: -0.1700
Data Index: 5640258 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9454. Min Act: -0.1700
Data Index: 5752338 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9282. Min Act: -0.1700
Data Index: 1218263 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9282. Min Act: -0.1700
Data Index: 6624880 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9282. Min Act: -0.1700
Data Index: 6166702 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9282. Min Act: -0.1700
Data Index: 2893159 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9454. Min Act: -0.1700
Data Index: 3579090 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9282. Min Act: -0.1700
Data Index: 7529229 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9110. Min Act: -0.1700
Data Index: 3304285 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9110. Min Act: -0.1700
Data Index: 8502937 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9110. Min Act: -0.1700
Data Index: 446858 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9110. Min Act: -0.1700
Data Index: 7385660 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.8939. Min Act: -0.1700
Data Index: 153364 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9110. Min Act: -0.1700
Data Index: 6709930 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.9110. Min Act: -0.1700
Data Index: 1747637 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0146. Min Range: -1.0146
Max Act: 0.8768. Min Act: -0.1700
Data Index: 4024257 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19