Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 962 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.5576. Min Act: -0.1700
Data Index: 8712468 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.5576. Min Act: -0.1700
Data Index: 3304928 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.5576. Min Act: -0.1700
Data Index: 1009998 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.5263. Min Act: -0.1700
Data Index: 8177587 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.5263. Min Act: -0.1700
Data Index: 5732955 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4950. Min Act: -0.1700
Data Index: 1147147 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4950. Min Act: -0.1700
Data Index: 2468092 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4950. Min Act: -0.1700
Data Index: 5462247 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4950. Min Act: -0.1700
Data Index: 5197581 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4637. Min Act: -0.1700
Data Index: 7395136 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4637. Min Act: -0.1700
Data Index: 4400937 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4323. Min Act: -0.1700
Data Index: 3107861 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4323. Min Act: -0.1700
Data Index: 5665834 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4637. Min Act: -0.1700
Data Index: 8441649 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4637. Min Act: -0.1700
Data Index: 3389344 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4010. Min Act: -0.1700
Data Index: 5234965 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4010. Min Act: -0.1700
Data Index: 6758315 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4010. Min Act: -0.1700
Data Index: 6368805 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4010. Min Act: -0.1700
Data Index: 6019221 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5576. Min Range: -3.5576
Max Act: 3.4010. Min Act: -0.1700
Data Index: 274116 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19