Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3120 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0035. Min Range: -1.0035
Max Act: 1.0035. Min Act: -0.1700
Data Index: 4244630 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0035. Min Range: -1.0035
Max Act: 1.0035. Min Act: -0.1700
Data Index: 1674046 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9948. Min Act: -0.1700
Data Index: 3082398 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9862. Min Act: -0.1700
Data Index: 8717084 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9689. Min Act: -0.1700
Data Index: 5128535 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9602. Min Act: -0.1700
Data Index: 7170414 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9602. Min Act: -0.1700
Data Index: 3757358 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9602. Min Act: -0.1700
Data Index: 6209372 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9516. Min Act: -0.1700
Data Index: 8422050 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9602. Min Act: -0.1700
Data Index: 4592774 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9430. Min Act: -0.1700
Data Index: 8777546 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9430. Min Act: -0.1700
Data Index: 4336170 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9344. Min Act: -0.1700
Data Index: 6448910 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9430. Min Act: -0.1700
Data Index: 1263199 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9344. Min Act: -0.1700
Data Index: 5945249 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9258. Min Act: -0.1700
Data Index: 2495866 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9344. Min Act: -0.1700
Data Index: 6316659 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9430. Min Act: -0.1700
Data Index: 6548134 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9344. Min Act: -0.1700
Data Index: 3062742 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0035. Min Range: -1.0035
Max Act: 0.9344. Min Act: -0.1700
Data Index: 7163276 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19