Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 679 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.2934. Min Act: -0.1700
Data Index: 7109474 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.2309. Min Act: -0.1700
Data Index: 5981784 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.1371. Min Act: -0.1700
Data Index: 4082505 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2934. Min Range: -5.2934
Max Act: 5.0121. Min Act: -0.1700
Data Index: 5988219 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.9809. Min Act: -0.1700
Data Index: 3715741 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.9809. Min Act: -0.1700
Data Index: 5106125 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.9496. Min Act: -0.1700
Data Index: 3628005 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.9496. Min Act: -0.1700
Data Index: 176398 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.9809. Min Act: -0.1700
Data Index: 4401875 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.9496. Min Act: -0.1700
Data Index: 7233088 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.9184. Min Act: -0.1700
Data Index: 6722316 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.9184. Min Act: -0.1700
Data Index: 631304 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.9184. Min Act: -0.1700
Data Index: 8018340 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.8871. Min Act: -0.1700
Data Index: 6509021 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.8871. Min Act: -0.1700
Data Index: 116451 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.9184. Min Act: -0.1700
Data Index: 1248667 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.8559. Min Act: -0.1700
Data Index: 10853 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.8559. Min Act: -0.1700
Data Index: 4290416 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.8559. Min Act: -0.1700
Data Index: 6408551 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2934. Min Range: -5.2934
Max Act: 4.7933. Min Act: -0.1700
Data Index: 1185195 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19